EnigmaForge

▶ Try one instance yourself — the question is hidden in the story

The benchmark where a model must find the problem before it can solve it.

120

Worlds

600

Scored items

Models compared

gpt-6-astra · 80.3/100

Current leader

2026-09-24T03:37:15+00:00 · 600 instances · 120 world families · methodology under “Benchmark details”

The leaderboard at a glance

gpt-6-astra leads: task success 80.3/100 (482/600 items), fact F1 90.6/100, 550/600 items answered. Solid baselines: constraint-solver and story-copy bound the scale.

Score:

Task success (/100)

All scores are 0–100; higher is better. Deterministic baselines appear in the tables only: a perfect-information solver marks the ceiling, and a text-copier marks the floor at zero.

Open the full performance table (per metric: all-item and scored-only, with confidence intervals)

How to read this benchmark

What a model must do

Every item is a short story that hides a set of definite facts and a rule for what should happen next. The model reads the story and must report the facts it is sure of, plus the action the rule calls for. Everything is exact: a fact is right or wrong, an action is right or wrong.

Finding the problem is scored

The same world is presented three ways: as a plain list of rules, as a story with the question stated, and as a story with no question at all. Discovery retention shows how much performance survives when the model is not told what it is looking for — the benchmark's signature measure.

Three honesty checks

Reasoning discipline flags models that burn their entire thinking budget without producing an answer. Earned decisions counts actions that were correct with a fully correct world, separating insight from lucky guessing. A story-copying control is graded alongside every model and must score zero — if it doesn't, the leaderboard is void.

How to interpret the scores
Score (0–100)	What it means
Task success	Share of items where the model reported every fact exactly right and took the action the rule requires. The headline measure.
Fact F1	Balance of how many stated facts were right vs how many of the hidden facts were found. Forgives a few misses; punishes wrong claims.
Discovery retention	Performance without a stated question, relative to with one. 100 means finding the problem cost nothing.
Reasoning discipline	Share of items answered without running out of thinking budget first.
Earned decisions	Correct actions that came with a fully correct world — the no-luckiness measure.

Why it is different

How EnigmaForge differs
Typical benchmarks	EnigmaForge
The question is stated	The question is hidden in the story
Hand-written items	Every world is generated and machine-verified
One checked answer	Answer plus the rule that justifies it
A right-sounding guess scores	Guesses are measured and shown separately
Scores can be gamed by copying	Copying the source text scores zero

Every EnigmaForge item is a short mystery with a machine-checked answer. Here is how one is made, in plain terms.

1 · Write a hidden rulebook

Each world starts as a list of secret facts — which record says what — and clues that connect them. No story exists yet.

2 · Prove there is exactly one answer

A checker proves two things before anything is written down: the clues have exactly one possible set of facts, and every clue is needed — remove any one and other answers become possible. No broken puzzles.

3 · Hide it in a story

Each clue becomes one sentence, woven into a story with extra scenes that mean nothing. A second, differently written story hides the same puzzle, so a model can't memorise the wording.

4 · Ask, three ways

The same puzzle goes out three ways: as a bare list of rules, as a story with the question stated, and as a story with no question at all. The last version is the real test — the model must notice there is something to solve.

5 · Grade exactly, not generously

The model must state each fact as 'this record equals this value' and name the action the rule requires. Paraphrase and partial credit are not awarded: values are checked letter-for-letter against the secret rulebook.

6 · Score it four ways

Solving (did it get everything right?), discovery (what did it keep when the question was hidden?), discipline (did it answer instead of running out of thinking room?), and honesty (were its right answers earned, or lucky?).

A note on honesty: the story-copying control is graded alongside every model. It submits the raw text as its answer and must score zero — a standing proof that the leaderboard cannot be gamed by copying.

How scores work

All scores are 0-100; lower is worse. Headline measure: fact F1. Ranking: all-item task success, then all-item fact F1, then provider name. No weighted composite. Conditional means use scored-item denominators; all-item means include missing, filtered, invalid, and failed attempts as zero achieved success. Unadjudicated outcomes remain unavailable. Decisions and task success use policy-bearing items only. Derived diagnostics: discovery cost is the conditional-F1 drop from a stated task (explicit) to an unstated one (implicit) — the price of finding the problem; reasoning overflow is the share of items where the model exhausted max_tokens without visible output; educated guesses are decisions that were correct while the submitted world was not exactly right. Answered includes invalid content; valid means a schema-compliant scored answer. Confidence intervals resample world families, not realizations.

Recorded solver attempt costs only; not full experimental spend.

claude-sonnet-5: 155/600 attempts were blocked by the provider's content filter before any answer. These count as missing mass in all-item scores; treat this row as a lower bound, not a capability estimate.

claude-fable-5: 206/600 attempts were blocked by the provider's content filter before any answer. These count as missing mass in all-item scores; treat this row as a lower bound, not a capability estimate.

claude-opus-5: 176/600 attempts were blocked by the provider's content filter before any answer. These count as missing mass in all-item scores; treat this row as a lower bound, not a capability estimate.

kimi-k3: 157/600 attempts failed in transport (network/provider errors, no response). These count as missing mass in all-item scores; treat this row as a lower bound, not a capability estimate.

claude-fable-5.1: 585/600 attempts were blocked by the provider's content filter before any answer. These count as missing mass in all-item scores; treat this row as a lower bound, not a capability estimate.

Coverage and recorded costs
Provider	Expected	Recorded	Answered	Valid	Filtered	Transport error	Invalid response	Recorded attempt cost	Known-cost records
baseline:constraint-solver	600	600	600	600	0	0	0	—	0
baseline:forward-chain	600	600	600	600	0	0	0	—	0
gpt-6-astra	600	600	550	550	0	50	0	$41.1670	550
gpt-6-sol	600	600	600	598	0	0	2	$11.6764	600
gemini-3.7-flash	600	600	600	598	0	0	2	$4.8211	600
gpt-5.6-sol	600	600	600	600	0	0	0	$13.2369	600
gemini-3.8-flash	600	600	598	597	0	2	1	$5.7595	600
glm-5.3	600	600	563	557	0	36	7	$60.8358	600
gpt-5.6-terra	600	600	600	600	0	0	0	$13.2981	600
deepseek-4.1-flash	600	600	595	595	0	5	0	$4.2486	600
gemini-3.6-flash	600	600	600	596	0	0	4	$7.5967	600
deepseek-v4-pro	600	600	598	592	0	0	8	$17.2358	600
gpt-6-luna	600	600	600	599	0	0	1	$0.8073	600
claude-sonnet-5	600	600	445	429	155	0	16	$19.1364	450
gpt-5.6-luna	600	600	600	599	0	0	1	$1.6427	600
claude-opus-5.5	600	600	591	591	9	0	0	$25.7479	600
claude-fable-5	600	600	393	392	206	1	1	$61.8898	449
mimo-v2.6-flash	600	600	594	583	0	6	11	$0.7466	595
mimo-v2.6-pro	600	600	593	573	0	0	27	$2.5694	600
claude-opus-5	600	600	424	389	176	0	35	$27.3236	429
grok-4.6	600	600	600	600	0	0	0	$20.2564	600
kimi-k2.6	600	600	599	599	0	1	0	$26.2999	600
minimax-m3	600	600	597	585	0	0	15	$3.3520	600
qwen3.8-27b	600	600	600	585	0	0	15	$2.6885	600
kimi-k3	600	600	443	443	0	157	0	$12.1732	443
glm-5.3-flash	600	600	596	593	0	4	3	$3.2404	600
claude-haiku-4.5	600	600	600	591	0	0	9	$9.0504	600
glm-4.7-flash	600	600	565	543	0	34	23	$9.8742	600
claude-fable-5.1	600	600	14	14	585	1	0	$2.4004	14
baseline:direct-facts	600	600	600	600	0	0	0	—	0
baseline:story-copy	600	600	600	0	0	0	600	—	0

Levels are configured strata, not calibrated capability ceilings. Charts show scored-only fact F1 per provider; tables add all-item values and intervals (family clusters).

level · fact_f1 (/100)

scenario · fact_f1 (/100)

condition · fact_f1 (/100)

realization · fact_f1 (/100)

genre · fact_f1 (/100)

renderer · fact_f1 (/100)

level
Provider	level	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	0	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:constraint-solver	1	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:constraint-solver	2	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:constraint-solver	3	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:constraint-solver	4	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:constraint-solver	5	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:forward-chain	0	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:forward-chain	1	100	100	99.3% (n=100)	99.3% (n=100)	95.0% (n=100)	95.0% (n=100)	95.0% (n=100)	95.0% (n=100)
baseline:forward-chain	2	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:forward-chain	3	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
baseline:forward-chain	4	100	100	99.8% (n=100)	99.8% (n=100)	95.0% (n=100)	95.0% (n=100)	95.0% (n=100)	95.0% (n=100)
baseline:forward-chain	5	100	100	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)	100.0% (n=100)
gpt-6-astra	0	100	100	96.0% (n=100)	96.0% (n=100)	65.0% (n=100)	65.0% (n=100)	65.0% (n=100)	65.0% (n=100)
gpt-6-astra	1	100	97	96.0% (n=100)	99.0% (n=97)	82.0% (n=100)	84.5% (n=97)	82.0% (n=100)	84.5% (n=97)
gpt-6-astra	2	100	100	99.0% (n=100)	99.0% (n=100)	93.0% (n=100)	93.0% (n=100)	93.0% (n=100)	93.0% (n=100)
gpt-6-astra	3	100	98	97.7% (n=100)	99.7% (n=98)	93.0% (n=100)	94.9% (n=98)	93.0% (n=100)	94.9% (n=98)
gpt-6-astra	4	100	97	96.8% (n=100)	99.7% (n=97)	92.0% (n=100)	94.8% (n=97)	92.0% (n=100)	94.8% (n=97)
gpt-6-astra	5	100	58	57.7% (n=100)	99.5% (n=58)	57.0% (n=100)	98.3% (n=58)	57.0% (n=100)	98.3% (n=58)
gpt-6-sol	0	100	100	93.5% (n=100)	93.5% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)
gpt-6-sol	1	100	100	96.8% (n=100)	96.8% (n=100)	72.0% (n=100)	72.0% (n=100)	72.0% (n=100)	72.0% (n=100)
gpt-6-sol	2	100	100	96.4% (n=100)	96.4% (n=100)	68.0% (n=100)	68.0% (n=100)	68.0% (n=100)	68.0% (n=100)
gpt-6-sol	3	100	100	98.0% (n=100)	98.0% (n=100)	81.0% (n=100)	81.0% (n=100)	80.0% (n=100)	80.0% (n=100)
gpt-6-sol	4	100	100	98.0% (n=100)	98.0% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)
gpt-6-sol	5	100	100	97.2% (n=100)	97.2% (n=100)	84.0% (n=100)	84.0% (n=100)	84.0% (n=100)	84.0% (n=100)
gemini-3.7-flash	0	100	100	98.2% (n=100)	98.2% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)
gemini-3.7-flash	1	100	100	97.1% (n=100)	97.1% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)
gemini-3.7-flash	2	100	100	95.8% (n=100)	95.8% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)	81.0% (n=100)
gemini-3.7-flash	3	100	100	90.2% (n=100)	90.2% (n=100)	67.0% (n=100)	67.0% (n=100)	67.0% (n=100)	67.0% (n=100)
gemini-3.7-flash	4	100	100	83.3% (n=100)	83.3% (n=100)	53.0% (n=100)	53.0% (n=100)	53.0% (n=100)	53.0% (n=100)
gemini-3.7-flash	5	100	100	83.3% (n=100)	83.3% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)
gpt-5.6-sol	0	100	100	94.6% (n=100)	94.6% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)
gpt-5.6-sol	1	100	100	96.9% (n=100)	96.9% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)
gpt-5.6-sol	2	100	100	91.9% (n=100)	91.9% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)
gpt-5.6-sol	3	100	100	94.8% (n=100)	94.8% (n=100)	78.0% (n=100)	78.0% (n=100)	78.0% (n=100)	78.0% (n=100)
gpt-5.6-sol	4	100	100	85.4% (n=100)	85.4% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)
gpt-5.6-sol	5	100	100	82.5% (n=100)	82.5% (n=100)	67.0% (n=100)	67.0% (n=100)	67.0% (n=100)	67.0% (n=100)
gemini-3.8-flash	0	100	100	96.7% (n=100)	96.7% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)	71.0% (n=100)
gemini-3.8-flash	1	100	100	96.4% (n=100)	96.4% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)	70.0% (n=100)
gemini-3.8-flash	2	100	99	90.2% (n=100)	91.1% (n=99)	63.0% (n=100)	63.6% (n=99)	63.0% (n=100)	63.6% (n=99)
gemini-3.8-flash	3	100	100	84.3% (n=100)	84.3% (n=100)	59.0% (n=100)	59.0% (n=100)	59.0% (n=100)	59.0% (n=100)
gemini-3.8-flash	4	100	99	76.6% (n=100)	77.4% (n=99)	50.0% (n=100)	50.5% (n=99)	50.0% (n=100)	50.5% (n=99)
gemini-3.8-flash	5	100	100	73.2% (n=100)	73.2% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)
glm-5.3	0	100	98	89.6% (n=100)	91.4% (n=98)	57.0% (n=100)	58.2% (n=98)	57.0% (n=100)	58.2% (n=98)
glm-5.3	1	100	95	90.5% (n=100)	95.3% (n=95)	66.0% (n=100)	69.5% (n=95)	66.0% (n=100)	69.5% (n=95)
glm-5.3	2	100	93	90.1% (n=100)	96.8% (n=93)	76.0% (n=100)	81.7% (n=93)	76.0% (n=100)	81.7% (n=93)
glm-5.3	3	100	94	77.4% (n=100)	82.3% (n=94)	47.0% (n=100)	50.0% (n=94)	46.0% (n=100)	48.9% (n=94)
glm-5.3	4	100	93	69.4% (n=100)	73.9% (n=94)	38.0% (n=100)	40.4% (n=94)	38.0% (n=100)	40.4% (n=94)
glm-5.3	5	100	90	63.6% (n=100)	70.6% (n=90)	36.0% (n=100)	40.0% (n=90)	36.0% (n=100)	40.0% (n=90)
gpt-5.6-terra	0	100	100	90.0% (n=100)	90.0% (n=100)	51.0% (n=100)	51.0% (n=100)	51.0% (n=100)	51.0% (n=100)
gpt-5.6-terra	1	100	100	86.1% (n=100)	86.1% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)
gpt-5.6-terra	2	100	100	84.7% (n=100)	84.7% (n=100)	59.0% (n=100)	59.0% (n=100)	59.0% (n=100)	59.0% (n=100)
gpt-5.6-terra	3	100	100	82.1% (n=100)	82.1% (n=100)	49.0% (n=100)	49.0% (n=100)	49.0% (n=100)	49.0% (n=100)
gpt-5.6-terra	4	100	100	76.5% (n=100)	76.5% (n=100)	47.0% (n=100)	47.0% (n=100)	47.0% (n=100)	47.0% (n=100)
gpt-5.6-terra	5	100	100	71.1% (n=100)	71.1% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)
deepseek-4.1-flash	0	100	100	91.8% (n=100)	91.8% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)	60.0% (n=100)
deepseek-4.1-flash	1	100	100	87.3% (n=100)	87.3% (n=100)	57.0% (n=100)	57.0% (n=100)	57.0% (n=100)	57.0% (n=100)
deepseek-4.1-flash	2	100	100	83.3% (n=100)	83.3% (n=100)	55.0% (n=100)	55.0% (n=100)	55.0% (n=100)	55.0% (n=100)
deepseek-4.1-flash	3	100	100	77.1% (n=100)	77.1% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)
deepseek-4.1-flash	4	100	96	66.1% (n=100)	68.9% (n=96)	39.0% (n=100)	40.6% (n=96)	39.0% (n=100)	40.6% (n=96)
deepseek-4.1-flash	5	100	99	66.6% (n=100)	67.2% (n=99)	35.0% (n=100)	35.4% (n=99)	35.0% (n=100)	35.4% (n=99)
gemini-3.6-flash	0	100	100	95.4% (n=100)	95.4% (n=100)	68.0% (n=100)	68.0% (n=100)	68.0% (n=100)	68.0% (n=100)
gemini-3.6-flash	1	100	100	90.3% (n=100)	90.3% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)	54.0% (n=100)
gemini-3.6-flash	2	100	100	86.4% (n=100)	86.4% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)
gemini-3.6-flash	3	100	100	75.4% (n=100)	75.4% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)
gemini-3.6-flash	4	100	100	68.9% (n=100)	68.9% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)
gemini-3.6-flash	5	100	100	60.6% (n=100)	60.6% (n=100)	26.0% (n=100)	26.0% (n=100)	26.0% (n=100)	26.0% (n=100)
deepseek-v4-pro	0	100	100	91.6% (n=100)	91.6% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)
deepseek-v4-pro	1	100	99	92.8% (n=100)	92.8% (n=100)	52.0% (n=100)	52.0% (n=100)	52.0% (n=100)	52.0% (n=100)
deepseek-v4-pro	2	100	100	93.2% (n=100)	93.2% (n=100)	47.0% (n=100)	47.0% (n=100)	47.0% (n=100)	47.0% (n=100)
deepseek-v4-pro	3	100	100	90.8% (n=100)	90.8% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)
deepseek-v4-pro	4	100	100	92.6% (n=100)	92.6% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)
deepseek-v4-pro	5	100	99	88.0% (n=100)	88.0% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)
gpt-6-luna	0	100	100	89.8% (n=100)	89.8% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)
gpt-6-luna	1	100	100	86.7% (n=100)	86.7% (n=100)	50.0% (n=100)	50.0% (n=100)	50.0% (n=100)	50.0% (n=100)
gpt-6-luna	2	100	100	80.5% (n=100)	80.5% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)
gpt-6-luna	3	100	100	85.2% (n=100)	85.2% (n=100)	43.0% (n=100)	43.0% (n=100)	43.0% (n=100)	43.0% (n=100)
gpt-6-luna	4	100	100	73.9% (n=100)	73.9% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)
gpt-6-luna	5	100	100	72.6% (n=100)	72.6% (n=100)	37.0% (n=100)	37.0% (n=100)	36.0% (n=100)	36.0% (n=100)
claude-sonnet-5	0	100	88	81.2% (n=100)	92.2% (n=88)	55.0% (n=100)	62.5% (n=88)	55.0% (n=100)	62.5% (n=88)
claude-sonnet-5	1	100	72	68.9% (n=100)	95.7% (n=72)	46.0% (n=100)	63.9% (n=72)	46.0% (n=100)	63.9% (n=72)
claude-sonnet-5	2	100	73	68.6% (n=100)	94.0% (n=73)	45.0% (n=100)	61.6% (n=73)	45.0% (n=100)	61.6% (n=73)
claude-sonnet-5	3	100	72	64.3% (n=100)	89.3% (n=72)	38.0% (n=100)	52.8% (n=72)	38.0% (n=100)	52.8% (n=72)
claude-sonnet-5	4	100	61	52.0% (n=100)	85.2% (n=61)	33.0% (n=100)	54.1% (n=61)	33.0% (n=100)	54.1% (n=61)
claude-sonnet-5	5	100	79	66.6% (n=100)	84.3% (n=79)	34.0% (n=100)	43.0% (n=79)	34.0% (n=100)	43.0% (n=79)
gpt-5.6-luna	0	100	100	88.6% (n=100)	88.6% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)
gpt-5.6-luna	1	100	100	83.3% (n=100)	83.3% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)
gpt-5.6-luna	2	100	100	73.8% (n=100)	73.8% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)
gpt-5.6-luna	3	100	100	85.7% (n=100)	85.7% (n=100)	41.0% (n=100)	41.0% (n=100)	40.0% (n=100)	40.0% (n=100)
gpt-5.6-luna	4	100	100	80.6% (n=100)	80.6% (n=100)	44.0% (n=100)	44.0% (n=100)	42.0% (n=100)	42.0% (n=100)
gpt-5.6-luna	5	100	100	76.2% (n=100)	76.2% (n=100)	39.0% (n=100)	39.0% (n=100)	36.0% (n=100)	36.0% (n=100)
claude-opus-5.5	0	100	100	93.2% (n=100)	93.2% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)
claude-opus-5.5	1	100	99	91.9% (n=100)	92.8% (n=99)	34.0% (n=100)	34.3% (n=99)	33.0% (n=100)	33.3% (n=99)
claude-opus-5.5	2	100	97	90.1% (n=100)	92.9% (n=97)	40.0% (n=100)	41.2% (n=97)	40.0% (n=100)	41.2% (n=97)
claude-opus-5.5	3	100	100	94.3% (n=100)	94.3% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)
claude-opus-5.5	4	100	98	91.4% (n=100)	93.2% (n=98)	41.0% (n=100)	41.8% (n=98)	41.0% (n=100)	41.8% (n=98)
claude-opus-5.5	5	100	97	90.4% (n=100)	93.2% (n=97)	45.0% (n=100)	46.4% (n=97)	45.0% (n=100)	46.4% (n=97)
claude-fable-5	0	100	75	72.3% (n=100)	96.4% (n=75)	48.0% (n=100)	64.0% (n=75)	48.0% (n=100)	64.0% (n=75)
claude-fable-5	1	100	68	65.1% (n=100)	95.8% (n=68)	47.0% (n=100)	69.1% (n=68)	47.0% (n=100)	69.1% (n=68)
claude-fable-5	2	100	59	54.7% (n=100)	92.7% (n=59)	28.0% (n=100)	47.5% (n=59)	28.0% (n=100)	47.5% (n=59)
claude-fable-5	3	100	65	61.7% (n=100)	95.0% (n=65)	38.0% (n=100)	58.5% (n=65)	38.0% (n=100)	58.5% (n=65)
claude-fable-5	4	100	66	63.3% (n=100)	95.8% (n=66)	36.0% (n=100)	54.5% (n=66)	36.0% (n=100)	54.5% (n=66)
claude-fable-5	5	100	60	58.1% (n=100)	96.9% (n=60)	40.0% (n=100)	66.7% (n=60)	40.0% (n=100)	66.7% (n=60)
mimo-v2.6-flash	0	100	95	85.7% (n=100)	90.2% (n=95)	50.0% (n=100)	52.6% (n=95)	50.0% (n=100)	52.6% (n=95)
mimo-v2.6-flash	1	100	100	86.7% (n=100)	86.7% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)
mimo-v2.6-flash	2	100	100	86.2% (n=100)	86.2% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)
mimo-v2.6-flash	3	100	100	74.1% (n=100)	74.1% (n=100)	37.0% (n=100)	37.0% (n=100)	34.0% (n=100)	34.0% (n=100)
mimo-v2.6-flash	4	100	99	74.5% (n=100)	75.2% (n=99)	36.0% (n=100)	36.4% (n=99)	31.0% (n=100)	31.3% (n=99)
mimo-v2.6-flash	5	100	100	64.0% (n=100)	64.0% (n=100)	32.0% (n=100)	32.0% (n=100)	30.0% (n=100)	30.0% (n=100)
mimo-v2.6-pro	0	100	99	89.2% (n=100)	89.2% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)
mimo-v2.6-pro	1	100	99	85.6% (n=100)	85.6% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)	46.0% (n=100)
mimo-v2.6-pro	2	100	99	81.5% (n=100)	81.5% (n=100)	45.0% (n=100)	45.0% (n=100)	43.0% (n=100)	43.0% (n=100)
mimo-v2.6-pro	3	100	100	73.9% (n=100)	73.9% (n=100)	38.0% (n=100)	38.0% (n=100)	37.0% (n=100)	37.0% (n=100)
mimo-v2.6-pro	4	100	99	68.4% (n=100)	68.4% (n=100)	34.0% (n=100)	34.0% (n=100)	32.0% (n=100)	32.0% (n=100)
mimo-v2.6-pro	5	100	97	61.0% (n=100)	61.0% (n=100)	27.0% (n=100)	27.0% (n=100)	25.0% (n=100)	25.0% (n=100)
claude-opus-5	0	100	75	68.7% (n=100)	91.5% (n=75)	40.0% (n=100)	53.3% (n=75)	40.0% (n=100)	53.3% (n=75)
claude-opus-5	1	100	70	59.2% (n=100)	84.6% (n=70)	35.0% (n=100)	50.0% (n=70)	35.0% (n=100)	50.0% (n=70)
claude-opus-5	2	100	71	57.0% (n=100)	80.3% (n=71)	40.0% (n=100)	56.3% (n=71)	40.0% (n=100)	56.3% (n=71)
claude-opus-5	3	100	63	50.3% (n=100)	79.9% (n=63)	33.0% (n=100)	52.4% (n=63)	33.0% (n=100)	52.4% (n=63)
claude-opus-5	4	100	73	52.2% (n=100)	71.5% (n=73)	36.0% (n=100)	49.3% (n=73)	36.0% (n=100)	49.3% (n=73)
claude-opus-5	5	100	72	56.4% (n=100)	78.3% (n=72)	39.0% (n=100)	54.2% (n=72)	39.0% (n=100)	54.2% (n=72)
grok-4.6	0	100	100	90.1% (n=100)	90.1% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)
grok-4.6	1	100	100	90.6% (n=100)	90.6% (n=100)	40.0% (n=100)	40.0% (n=100)	40.0% (n=100)	40.0% (n=100)
grok-4.6	2	100	100	89.4% (n=100)	89.4% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)
grok-4.6	3	100	100	90.1% (n=100)	90.1% (n=100)	37.0% (n=100)	37.0% (n=100)	37.0% (n=100)	37.0% (n=100)
grok-4.6	4	100	100	89.6% (n=100)	89.6% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)
grok-4.6	5	100	100	87.2% (n=100)	87.2% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)	44.0% (n=100)
kimi-k2.6	0	100	100	93.5% (n=100)	93.5% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)	48.0% (n=100)
kimi-k2.6	1	100	100	93.3% (n=100)	93.3% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)	39.0% (n=100)
kimi-k2.6	2	100	100	91.7% (n=100)	91.7% (n=100)	34.0% (n=100)	34.0% (n=100)	34.0% (n=100)	34.0% (n=100)
kimi-k2.6	3	100	100	88.8% (n=100)	88.8% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)
kimi-k2.6	4	100	100	88.1% (n=100)	88.1% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)	33.0% (n=100)
kimi-k2.6	5	100	99	86.9% (n=100)	87.8% (n=99)	29.0% (n=100)	29.3% (n=99)	29.0% (n=100)	29.3% (n=99)
minimax-m3	0	100	100	87.6% (n=100)	87.6% (n=100)	43.0% (n=100)	43.0% (n=100)	43.0% (n=100)	43.0% (n=100)
minimax-m3	1	100	98	76.9% (n=100)	76.9% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)	41.0% (n=100)
minimax-m3	2	100	100	68.3% (n=100)	68.3% (n=100)	34.0% (n=100)	34.0% (n=100)	34.0% (n=100)	34.0% (n=100)
minimax-m3	3	100	100	65.2% (n=100)	65.2% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)	32.0% (n=100)
minimax-m3	4	100	99	60.3% (n=100)	60.3% (n=100)	28.0% (n=100)	28.0% (n=100)	28.0% (n=100)	28.0% (n=100)
minimax-m3	5	100	100	52.5% (n=100)	52.5% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)
qwen3.8-27b	0	100	100	92.4% (n=100)	92.4% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)	45.0% (n=100)
qwen3.8-27b	1	100	100	87.4% (n=100)	87.4% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)
qwen3.8-27b	2	100	100	87.6% (n=100)	87.6% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)	42.0% (n=100)
qwen3.8-27b	3	100	100	86.1% (n=100)	86.1% (n=100)	28.0% (n=100)	28.0% (n=100)	28.0% (n=100)	28.0% (n=100)
qwen3.8-27b	4	100	100	75.5% (n=100)	75.5% (n=100)	22.0% (n=100)	22.0% (n=100)	22.0% (n=100)	22.0% (n=100)
qwen3.8-27b	5	100	100	72.9% (n=100)	72.9% (n=100)	29.0% (n=100)	29.0% (n=100)	29.0% (n=100)	29.0% (n=100)
kimi-k3	0	100	96	90.6% (n=100)	94.4% (n=96)	52.0% (n=100)	54.2% (n=96)	52.0% (n=100)	54.2% (n=96)
kimi-k3	1	100	84	77.7% (n=100)	92.5% (n=84)	40.0% (n=100)	47.6% (n=84)	40.0% (n=100)	47.6% (n=84)
kimi-k3	2	100	99	88.9% (n=100)	89.8% (n=99)	42.0% (n=100)	42.4% (n=99)	42.0% (n=100)	42.4% (n=99)
kimi-k3	3	100	100	76.6% (n=100)	76.6% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)	36.0% (n=100)
kimi-k3	4	100	63	42.7% (n=100)	67.8% (n=63)	17.0% (n=100)	27.0% (n=63)	17.0% (n=100)	27.0% (n=63)
kimi-k3	5	100	1	0.1% (n=100)	13.3% (n=1)	0.0% (n=100)	0.0% (n=1)	0.0% (n=100)	0.0% (n=1)
glm-5.3-flash	0	100	99	86.6% (n=100)	87.5% (n=99)	35.0% (n=100)	35.4% (n=99)	35.0% (n=100)	35.4% (n=99)
glm-5.3-flash	1	100	98	79.8% (n=100)	81.5% (n=98)	33.0% (n=100)	33.7% (n=98)	33.0% (n=100)	33.7% (n=98)
glm-5.3-flash	2	100	99	73.5% (n=100)	74.3% (n=99)	29.0% (n=100)	29.3% (n=99)	29.0% (n=100)	29.3% (n=99)
glm-5.3-flash	3	100	100	61.3% (n=100)	61.3% (n=100)	21.0% (n=100)	21.0% (n=100)	21.0% (n=100)	21.0% (n=100)
glm-5.3-flash	4	100	100	54.1% (n=100)	54.1% (n=100)	19.0% (n=100)	19.0% (n=100)	19.0% (n=100)	19.0% (n=100)
glm-5.3-flash	5	100	100	44.7% (n=100)	44.7% (n=100)	19.0% (n=100)	19.0% (n=100)	18.0% (n=100)	18.0% (n=100)
claude-haiku-4.5	0	100	100	83.4% (n=100)	83.4% (n=100)	31.0% (n=100)	31.0% (n=100)	31.0% (n=100)	31.0% (n=100)
claude-haiku-4.5	1	100	100	78.8% (n=100)	78.8% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)
claude-haiku-4.5	2	100	100	71.5% (n=100)	71.5% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)	25.0% (n=100)
claude-haiku-4.5	3	100	100	60.2% (n=100)	60.2% (n=100)	20.0% (n=100)	20.0% (n=100)	20.0% (n=100)	20.0% (n=100)
claude-haiku-4.5	4	100	100	57.3% (n=100)	57.3% (n=100)	19.0% (n=100)	19.0% (n=100)	19.0% (n=100)	19.0% (n=100)
claude-haiku-4.5	5	100	100	57.1% (n=100)	57.1% (n=100)	22.0% (n=100)	22.0% (n=100)	22.0% (n=100)	22.0% (n=100)
glm-4.7-flash	0	100	99	68.4% (n=100)	69.0% (n=99)	28.0% (n=100)	28.3% (n=99)	28.0% (n=100)	28.3% (n=99)
glm-4.7-flash	1	100	100	76.0% (n=100)	76.0% (n=100)	27.0% (n=100)	27.0% (n=100)	27.0% (n=100)	27.0% (n=100)
glm-4.7-flash	2	100	98	70.7% (n=100)	72.1% (n=98)	19.0% (n=100)	19.4% (n=98)	19.0% (n=100)	19.4% (n=98)
glm-4.7-flash	3	100	85	53.0% (n=100)	61.6% (n=86)	17.0% (n=100)	19.8% (n=86)	17.0% (n=100)	19.8% (n=86)
glm-4.7-flash	4	100	87	55.8% (n=100)	64.1% (n=87)	11.0% (n=100)	12.6% (n=87)	11.0% (n=100)	12.6% (n=87)
glm-4.7-flash	5	100	96	56.0% (n=100)	58.3% (n=96)	15.0% (n=100)	15.6% (n=96)	15.0% (n=100)	15.6% (n=96)
claude-fable-5.1	0	100	1	1.0% (n=100)	100.0% (n=1)	1.0% (n=100)	100.0% (n=1)	1.0% (n=100)	100.0% (n=1)
claude-fable-5.1	1	100	0	0.0% (n=100)	— (n=0)	0.0% (n=100)	— (n=0)	0.0% (n=100)	— (n=0)
claude-fable-5.1	2	100	0	0.0% (n=100)	— (n=0)	0.0% (n=100)	— (n=0)	0.0% (n=100)	— (n=0)
claude-fable-5.1	3	100	1	1.0% (n=100)	100.0% (n=1)	1.0% (n=100)	100.0% (n=1)	1.0% (n=100)	100.0% (n=1)
claude-fable-5.1	4	100	5	4.9% (n=100)	97.8% (n=5)	3.0% (n=100)	60.0% (n=5)	3.0% (n=100)	60.0% (n=5)
claude-fable-5.1	5	100	7	6.9% (n=100)	98.1% (n=7)	5.0% (n=100)	71.4% (n=7)	5.0% (n=100)	71.4% (n=7)
baseline:direct-facts	0	100	100	80.6% (n=100)	80.6% (n=100)	5.0% (n=100)	5.0% (n=100)	5.0% (n=100)	5.0% (n=100)
baseline:direct-facts	1	100	100	73.0% (n=100)	73.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:direct-facts	2	100	100	77.0% (n=100)	77.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:direct-facts	3	100	100	71.1% (n=100)	71.1% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:direct-facts	4	100	100	71.7% (n=100)	71.7% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:direct-facts	5	100	100	68.8% (n=100)	68.8% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	0	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	1	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	2	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	3	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	4	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)
baseline:story-copy	5	100	100	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)	0.0% (n=100)

scenario
Provider	scenario	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	strata	600	600	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)
baseline:forward-chain	strata	600	600	99.8% (n=600)	99.8% (n=600)	98.3% (n=600)	98.3% (n=600)	98.3% (n=600)	98.3% (n=600)
gpt-6-astra	strata	600	550	90.6% (n=600)	98.8% (n=550)	80.3% (n=600)	87.6% (n=550)	80.3% (n=600)	87.6% (n=550)
gpt-6-sol	strata	600	600	96.6% (n=600)	96.6% (n=600)	74.3% (n=600)	74.3% (n=600)	74.2% (n=600)	74.2% (n=600)
gemini-3.7-flash	strata	600	600	91.3% (n=600)	91.3% (n=600)	68.7% (n=600)	68.7% (n=600)	68.7% (n=600)	68.7% (n=600)
gpt-5.6-sol	strata	600	600	91.0% (n=600)	91.0% (n=600)	68.5% (n=600)	68.5% (n=600)	68.5% (n=600)	68.5% (n=600)
gemini-3.8-flash	strata	600	598	86.2% (n=600)	86.5% (n=598)	59.0% (n=600)	59.2% (n=598)	59.0% (n=600)	59.2% (n=598)
glm-5.3	strata	600	563	80.1% (n=600)	85.2% (n=564)	53.3% (n=600)	56.7% (n=564)	53.2% (n=600)	56.6% (n=564)
gpt-5.6-terra	strata	600	600	81.8% (n=600)	81.8% (n=600)	50.7% (n=600)	50.7% (n=600)	50.7% (n=600)	50.7% (n=600)
deepseek-4.1-flash	strata	600	595	78.7% (n=600)	79.4% (n=595)	48.7% (n=600)	49.1% (n=595)	48.7% (n=600)	49.1% (n=595)
gemini-3.6-flash	strata	600	600	79.5% (n=600)	79.5% (n=600)	43.7% (n=600)	43.7% (n=600)	43.7% (n=600)	43.7% (n=600)
deepseek-v4-pro	strata	600	598	91.5% (n=600)	91.5% (n=600)	42.7% (n=600)	42.7% (n=600)	42.7% (n=600)	42.7% (n=600)
gpt-6-luna	strata	600	600	81.5% (n=600)	81.5% (n=600)	42.5% (n=600)	42.5% (n=600)	42.3% (n=600)	42.3% (n=600)
claude-sonnet-5	strata	600	445	66.9% (n=600)	90.2% (n=445)	41.8% (n=600)	56.4% (n=445)	41.8% (n=600)	56.4% (n=445)
gpt-5.6-luna	strata	600	600	81.4% (n=600)	81.4% (n=600)	42.7% (n=600)	42.7% (n=600)	41.7% (n=600)	41.7% (n=600)
claude-opus-5.5	strata	600	591	91.9% (n=600)	93.3% (n=591)	40.0% (n=600)	40.6% (n=591)	39.8% (n=600)	40.4% (n=591)
claude-fable-5	strata	600	393	62.5% (n=600)	95.5% (n=393)	39.5% (n=600)	60.3% (n=393)	39.5% (n=600)	60.3% (n=393)
mimo-v2.6-flash	strata	600	594	78.5% (n=600)	79.3% (n=594)	40.5% (n=600)	40.9% (n=594)	38.8% (n=600)	39.2% (n=594)
mimo-v2.6-pro	strata	600	593	76.6% (n=600)	76.6% (n=600)	39.2% (n=600)	39.2% (n=600)	38.0% (n=600)	38.0% (n=600)
claude-opus-5	strata	600	424	57.3% (n=600)	81.1% (n=424)	37.2% (n=600)	52.6% (n=424)	37.2% (n=600)	52.6% (n=424)
grok-4.6	strata	600	600	89.5% (n=600)	89.5% (n=600)	37.0% (n=600)	37.0% (n=600)	37.0% (n=600)	37.0% (n=600)
kimi-k2.6	strata	600	599	90.4% (n=600)	90.6% (n=599)	36.5% (n=600)	36.6% (n=599)	36.5% (n=600)	36.6% (n=599)
minimax-m3	strata	600	597	68.5% (n=600)	68.5% (n=600)	33.8% (n=600)	33.8% (n=600)	33.8% (n=600)	33.8% (n=600)
qwen3.8-27b	strata	600	600	83.6% (n=600)	83.6% (n=600)	33.7% (n=600)	33.7% (n=600)	33.7% (n=600)	33.7% (n=600)
kimi-k3	strata	600	443	62.8% (n=600)	85.0% (n=443)	31.2% (n=600)	42.2% (n=443)	31.2% (n=600)	42.2% (n=443)
glm-5.3-flash	strata	600	596	66.7% (n=600)	67.1% (n=596)	26.0% (n=600)	26.2% (n=596)	25.8% (n=600)	26.0% (n=596)
claude-haiku-4.5	strata	600	600	68.0% (n=600)	68.0% (n=600)	23.7% (n=600)	23.7% (n=600)	23.7% (n=600)	23.7% (n=600)
glm-4.7-flash	strata	600	565	63.3% (n=600)	67.1% (n=566)	19.5% (n=600)	20.7% (n=566)	19.5% (n=600)	20.7% (n=566)
claude-fable-5.1	strata	600	14	2.3% (n=600)	98.2% (n=14)	1.7% (n=600)	71.4% (n=14)	1.7% (n=600)	71.4% (n=14)
baseline:direct-facts	strata	600	600	73.7% (n=600)	73.7% (n=600)	0.8% (n=600)	0.8% (n=600)	0.8% (n=600)	0.8% (n=600)
baseline:story-copy	strata	600	600	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)

condition
Provider	condition	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	explicit	240	240	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)
baseline:constraint-solver	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
baseline:constraint-solver	implicit	240	240	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)
baseline:forward-chain	explicit	240	240	99.8% (n=240)	99.8% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)
baseline:forward-chain	formal	120	120	99.8% (n=120)	99.8% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
baseline:forward-chain	implicit	240	240	99.8% (n=240)	99.8% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)
gpt-6-astra	explicit	240	220	90.8% (n=240)	99.1% (n=220)	81.2% (n=240)	88.6% (n=220)	81.2% (n=240)	88.6% (n=220)
gpt-6-astra	formal	120	114	95.0% (n=120)	100.0% (n=114)	95.0% (n=120)	100.0% (n=114)	95.0% (n=120)	100.0% (n=114)
gpt-6-astra	implicit	240	216	88.0% (n=240)	97.8% (n=216)	72.1% (n=240)	80.1% (n=216)	72.1% (n=240)	80.1% (n=216)
gpt-6-sol	explicit	240	240	95.0% (n=240)	95.0% (n=240)	61.3% (n=240)	61.3% (n=240)	60.8% (n=240)	60.8% (n=240)
gpt-6-sol	formal	120	120	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)
gpt-6-sol	implicit	240	240	97.1% (n=240)	97.1% (n=240)	75.0% (n=240)	75.0% (n=240)	75.0% (n=240)	75.0% (n=240)
gemini-3.7-flash	explicit	240	240	96.9% (n=240)	96.9% (n=240)	68.8% (n=240)	68.8% (n=240)	68.8% (n=240)	68.8% (n=240)
gemini-3.7-flash	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.7-flash	implicit	240	240	81.4% (n=240)	81.4% (n=240)	52.9% (n=240)	52.9% (n=240)	52.9% (n=240)	52.9% (n=240)
gpt-5.6-sol	explicit	240	240	97.2% (n=240)	97.2% (n=240)	67.1% (n=240)	67.1% (n=240)	67.1% (n=240)	67.1% (n=240)
gpt-5.6-sol	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gpt-5.6-sol	implicit	240	240	80.4% (n=240)	80.4% (n=240)	54.2% (n=240)	54.2% (n=240)	54.2% (n=240)	54.2% (n=240)
gemini-3.8-flash	explicit	240	239	95.0% (n=240)	95.3% (n=239)	58.3% (n=240)	58.6% (n=239)	58.3% (n=240)	58.6% (n=239)
gemini-3.8-flash	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.8-flash	implicit	240	239	70.6% (n=240)	70.9% (n=239)	39.2% (n=240)	39.3% (n=239)	39.2% (n=240)	39.3% (n=239)
glm-5.3	explicit	240	216	77.2% (n=240)	85.7% (n=216)	48.3% (n=240)	53.7% (n=216)	47.9% (n=240)	53.2% (n=216)
glm-5.3	formal	120	120	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
glm-5.3	implicit	240	227	73.9% (n=240)	77.8% (n=228)	35.8% (n=240)	37.7% (n=228)	35.8% (n=240)	37.7% (n=228)
gpt-5.6-terra	explicit	240	240	96.3% (n=240)	96.3% (n=240)	52.5% (n=240)	52.5% (n=240)	52.5% (n=240)	52.5% (n=240)
gpt-5.6-terra	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gpt-5.6-terra	implicit	240	240	58.1% (n=240)	58.1% (n=240)	24.2% (n=240)	24.2% (n=240)	24.2% (n=240)	24.2% (n=240)
deepseek-4.1-flash	explicit	240	236	93.7% (n=240)	95.3% (n=236)	53.8% (n=240)	54.7% (n=236)	53.8% (n=240)	54.7% (n=236)
deepseek-4.1-flash	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
deepseek-4.1-flash	implicit	240	239	53.1% (n=240)	53.3% (n=239)	17.9% (n=240)	18.0% (n=239)	17.9% (n=240)	18.0% (n=239)
gemini-3.6-flash	explicit	240	240	83.7% (n=240)	83.7% (n=240)	42.9% (n=240)	42.9% (n=240)	42.9% (n=240)	42.9% (n=240)
gemini-3.6-flash	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.6-flash	implicit	240	240	65.0% (n=240)	65.0% (n=240)	16.2% (n=240)	16.2% (n=240)	16.2% (n=240)	16.2% (n=240)
deepseek-v4-pro	explicit	240	239	92.7% (n=240)	92.7% (n=240)	38.8% (n=240)	38.8% (n=240)	38.8% (n=240)	38.8% (n=240)
deepseek-v4-pro	formal	120	120	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)
deepseek-v4-pro	implicit	240	239	87.3% (n=240)	87.3% (n=240)	19.2% (n=240)	19.2% (n=240)	19.2% (n=240)	19.2% (n=240)
gpt-6-luna	explicit	240	240	92.2% (n=240)	92.2% (n=240)	33.3% (n=240)	33.3% (n=240)	33.3% (n=240)	33.3% (n=240)
gpt-6-luna	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	99.2% (n=120)	99.2% (n=120)
gpt-6-luna	implicit	240	240	61.5% (n=240)	61.5% (n=240)	22.9% (n=240)	22.9% (n=240)	22.9% (n=240)	22.9% (n=240)
claude-sonnet-5	explicit	240	193	74.8% (n=240)	93.1% (n=193)	34.2% (n=240)	42.5% (n=193)	34.2% (n=240)	42.5% (n=193)
claude-sonnet-5	formal	120	120	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)
claude-sonnet-5	implicit	240	132	45.8% (n=240)	83.3% (n=132)	23.8% (n=240)	43.2% (n=132)	23.8% (n=240)	43.2% (n=132)
gpt-5.6-luna	explicit	240	240	94.5% (n=240)	94.5% (n=240)	40.0% (n=240)	40.0% (n=240)	38.3% (n=240)	38.3% (n=240)
gpt-5.6-luna	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	98.3% (n=120)	98.3% (n=120)
gpt-5.6-luna	implicit	240	240	58.9% (n=240)	58.9% (n=240)	16.7% (n=240)	16.7% (n=240)	16.7% (n=240)	16.7% (n=240)
claude-opus-5.5	explicit	240	235	90.8% (n=240)	92.8% (n=235)	28.3% (n=240)	28.9% (n=235)	27.9% (n=240)	28.5% (n=235)
claude-opus-5.5	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
claude-opus-5.5	implicit	240	236	88.8% (n=240)	90.3% (n=236)	21.7% (n=240)	22.0% (n=236)	21.7% (n=240)	22.0% (n=236)
claude-fable-5	explicit	240	161	62.8% (n=240)	93.7% (n=161)	34.6% (n=240)	51.6% (n=161)	34.6% (n=240)	51.6% (n=161)
claude-fable-5	formal	120	89	74.2% (n=120)	100.0% (n=89)	74.2% (n=120)	100.0% (n=89)	74.2% (n=120)	100.0% (n=89)
claude-fable-5	implicit	240	143	56.4% (n=240)	94.7% (n=143)	27.1% (n=240)	45.5% (n=143)	27.1% (n=240)	45.5% (n=143)
mimo-v2.6-flash	explicit	240	237	89.1% (n=240)	90.2% (n=237)	40.0% (n=240)	40.5% (n=237)	38.3% (n=240)	38.8% (n=237)
mimo-v2.6-flash	formal	120	120	96.3% (n=120)	96.3% (n=120)	95.0% (n=120)	95.0% (n=120)	91.7% (n=120)	91.7% (n=120)
mimo-v2.6-flash	implicit	240	237	59.0% (n=240)	59.8% (n=237)	13.8% (n=240)	13.9% (n=237)	12.9% (n=240)	13.1% (n=237)
mimo-v2.6-pro	explicit	240	233	84.6% (n=240)	84.6% (n=240)	38.8% (n=240)	38.8% (n=240)	36.7% (n=240)	36.7% (n=240)
mimo-v2.6-pro	formal	120	120	97.3% (n=120)	97.3% (n=120)	94.2% (n=120)	94.2% (n=120)	92.5% (n=120)	92.5% (n=120)
mimo-v2.6-pro	implicit	240	240	58.3% (n=240)	58.3% (n=240)	12.1% (n=240)	12.1% (n=240)	12.1% (n=240)	12.1% (n=240)
claude-opus-5	explicit	240	230	82.2% (n=240)	85.8% (n=230)	58.3% (n=240)	60.9% (n=230)	58.3% (n=240)	60.9% (n=230)
claude-opus-5	formal	120	0	0.0% (n=120)	— (n=0)	0.0% (n=120)	— (n=0)	0.0% (n=120)	— (n=0)
claude-opus-5	implicit	240	194	61.0% (n=240)	75.4% (n=194)	34.6% (n=240)	42.8% (n=194)	34.6% (n=240)	42.8% (n=194)
grok-4.6	explicit	240	240	88.0% (n=240)	88.0% (n=240)	21.2% (n=240)	21.2% (n=240)	21.2% (n=240)	21.2% (n=240)
grok-4.6	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
grok-4.6	implicit	240	240	85.7% (n=240)	85.7% (n=240)	21.2% (n=240)	21.2% (n=240)	21.2% (n=240)	21.2% (n=240)
kimi-k2.6	explicit	240	239	92.0% (n=240)	92.4% (n=239)	23.8% (n=240)	23.8% (n=239)	23.8% (n=240)	23.8% (n=239)
kimi-k2.6	formal	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
kimi-k2.6	implicit	240	240	84.0% (n=240)	84.0% (n=240)	17.5% (n=240)	17.5% (n=240)	17.5% (n=240)	17.5% (n=240)
minimax-m3	explicit	240	238	69.5% (n=240)	69.5% (n=240)	24.6% (n=240)	24.6% (n=240)	24.6% (n=240)	24.6% (n=240)
minimax-m3	formal	120	120	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)
minimax-m3	implicit	240	239	52.9% (n=240)	52.9% (n=240)	11.2% (n=240)	11.2% (n=240)	11.2% (n=240)	11.2% (n=240)
qwen3.8-27b	explicit	240	240	86.5% (n=240)	86.5% (n=240)	24.2% (n=240)	24.2% (n=240)	24.2% (n=240)	24.2% (n=240)
qwen3.8-27b	formal	120	120	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)
qwen3.8-27b	implicit	240	240	74.6% (n=240)	74.6% (n=240)	12.1% (n=240)	12.1% (n=240)	12.1% (n=240)	12.1% (n=240)
kimi-k3	explicit	240	171	60.6% (n=240)	85.0% (n=171)	18.8% (n=240)	26.3% (n=171)	18.8% (n=240)	26.3% (n=171)
kimi-k3	formal	120	93	77.5% (n=120)	100.0% (n=93)	77.5% (n=120)	100.0% (n=93)	77.5% (n=120)	100.0% (n=93)
kimi-k3	implicit	240	179	57.6% (n=240)	77.2% (n=179)	20.4% (n=240)	27.4% (n=179)	20.4% (n=240)	27.4% (n=179)
glm-5.3-flash	explicit	240	236	64.0% (n=240)	65.1% (n=236)	18.3% (n=240)	18.6% (n=236)	17.9% (n=240)	18.2% (n=236)
glm-5.3-flash	formal	120	120	99.0% (n=120)	99.0% (n=120)	83.3% (n=120)	83.3% (n=120)	83.3% (n=120)	83.3% (n=120)
glm-5.3-flash	implicit	240	240	53.2% (n=240)	53.2% (n=240)	5.0% (n=240)	5.0% (n=240)	5.0% (n=240)	5.0% (n=240)
claude-haiku-4.5	explicit	240	240	68.0% (n=240)	68.0% (n=240)	5.8% (n=240)	5.8% (n=240)	5.8% (n=240)	5.8% (n=240)
claude-haiku-4.5	formal	120	120	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
claude-haiku-4.5	implicit	240	240	53.0% (n=240)	53.0% (n=240)	4.2% (n=240)	4.2% (n=240)	4.2% (n=240)	4.2% (n=240)
glm-4.7-flash	explicit	240	221	59.1% (n=240)	63.9% (n=222)	6.7% (n=240)	7.2% (n=222)	6.7% (n=240)	7.2% (n=222)
glm-4.7-flash	formal	120	120	90.4% (n=120)	90.4% (n=120)	77.5% (n=120)	77.5% (n=120)	77.5% (n=120)	77.5% (n=120)
glm-4.7-flash	implicit	240	224	54.0% (n=240)	57.8% (n=224)	3.3% (n=240)	3.6% (n=224)	3.3% (n=240)	3.6% (n=224)
claude-fable-5.1	explicit	240	2	0.8% (n=240)	100.0% (n=2)	0.8% (n=240)	100.0% (n=2)	0.8% (n=240)	100.0% (n=2)
claude-fable-5.1	formal	120	3	2.5% (n=120)	100.0% (n=3)	2.5% (n=120)	100.0% (n=3)	2.5% (n=120)	100.0% (n=3)
claude-fable-5.1	implicit	240	9	3.6% (n=240)	97.3% (n=9)	2.1% (n=240)	55.6% (n=9)	2.1% (n=240)	55.6% (n=9)
baseline:direct-facts	explicit	240	240	73.7% (n=240)	73.7% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)
baseline:direct-facts	formal	120	120	73.7% (n=120)	73.7% (n=120)	0.8% (n=120)	0.8% (n=120)	0.8% (n=120)	0.8% (n=120)
baseline:direct-facts	implicit	240	240	73.7% (n=240)	73.7% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)
baseline:story-copy	explicit	240	240	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)
baseline:story-copy	formal	120	120	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)
baseline:story-copy	implicit	240	240	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)

realization
Provider	realization	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
baseline:constraint-solver	1	240	240	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)
baseline:constraint-solver	2	240	240	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)	100.0% (n=240)
baseline:forward-chain	0	120	120	99.8% (n=120)	99.8% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
baseline:forward-chain	1	240	240	99.8% (n=240)	99.8% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)
baseline:forward-chain	2	240	240	99.8% (n=240)	99.8% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)	98.3% (n=240)
gpt-6-astra	0	120	114	95.0% (n=120)	100.0% (n=114)	95.0% (n=120)	100.0% (n=114)	95.0% (n=120)	100.0% (n=114)
gpt-6-astra	1	240	223	91.4% (n=240)	98.4% (n=223)	79.2% (n=240)	85.2% (n=223)	79.2% (n=240)	85.2% (n=223)
gpt-6-astra	2	240	213	87.5% (n=240)	98.5% (n=213)	74.2% (n=240)	83.6% (n=213)	74.2% (n=240)	83.6% (n=213)
gpt-6-sol	0	120	120	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)	99.2% (n=120)
gpt-6-sol	1	240	240	96.1% (n=240)	96.1% (n=240)	70.4% (n=240)	70.4% (n=240)	70.4% (n=240)	70.4% (n=240)
gpt-6-sol	2	240	240	96.0% (n=240)	96.0% (n=240)	65.8% (n=240)	65.8% (n=240)	65.4% (n=240)	65.4% (n=240)
gemini-3.7-flash	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.7-flash	1	240	240	89.6% (n=240)	89.6% (n=240)	60.0% (n=240)	60.0% (n=240)	60.0% (n=240)	60.0% (n=240)
gemini-3.7-flash	2	240	240	88.7% (n=240)	88.7% (n=240)	61.7% (n=240)	61.7% (n=240)	61.7% (n=240)	61.7% (n=240)
gpt-5.6-sol	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gpt-5.6-sol	1	240	240	87.7% (n=240)	87.7% (n=240)	61.7% (n=240)	61.7% (n=240)	61.7% (n=240)	61.7% (n=240)
gpt-5.6-sol	2	240	240	89.8% (n=240)	89.8% (n=240)	59.6% (n=240)	59.6% (n=240)	59.6% (n=240)	59.6% (n=240)
gemini-3.8-flash	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.8-flash	1	240	239	81.8% (n=240)	82.1% (n=239)	49.6% (n=240)	49.8% (n=239)	49.6% (n=240)	49.8% (n=239)
gemini-3.8-flash	2	240	239	83.8% (n=240)	84.1% (n=239)	47.9% (n=240)	48.1% (n=239)	47.9% (n=240)	48.1% (n=239)
glm-5.3	0	120	120	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
glm-5.3	1	240	221	74.8% (n=240)	80.8% (n=222)	44.2% (n=240)	47.7% (n=222)	44.2% (n=240)	47.7% (n=222)
glm-5.3	2	240	222	76.2% (n=240)	82.4% (n=222)	40.0% (n=240)	43.2% (n=222)	39.6% (n=240)	42.8% (n=222)
gpt-5.6-terra	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gpt-5.6-terra	1	240	240	77.6% (n=240)	77.6% (n=240)	39.6% (n=240)	39.6% (n=240)	39.6% (n=240)	39.6% (n=240)
gpt-5.6-terra	2	240	240	76.8% (n=240)	76.8% (n=240)	37.1% (n=240)	37.1% (n=240)	37.1% (n=240)	37.1% (n=240)
deepseek-4.1-flash	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
deepseek-4.1-flash	1	240	236	73.9% (n=240)	75.1% (n=236)	37.1% (n=240)	37.7% (n=236)	37.1% (n=240)	37.7% (n=236)
deepseek-4.1-flash	2	240	239	72.9% (n=240)	73.2% (n=239)	34.6% (n=240)	34.7% (n=239)	34.6% (n=240)	34.7% (n=239)
gemini-3.6-flash	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
gemini-3.6-flash	1	240	240	74.5% (n=240)	74.5% (n=240)	30.0% (n=240)	30.0% (n=240)	30.0% (n=240)	30.0% (n=240)
gemini-3.6-flash	2	240	240	74.2% (n=240)	74.2% (n=240)	29.2% (n=240)	29.2% (n=240)	29.2% (n=240)	29.2% (n=240)
deepseek-v4-pro	0	120	120	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)
deepseek-v4-pro	1	240	238	89.0% (n=240)	89.0% (n=240)	29.2% (n=240)	29.2% (n=240)	29.2% (n=240)	29.2% (n=240)
deepseek-v4-pro	2	240	240	90.9% (n=240)	90.9% (n=240)	28.7% (n=240)	28.7% (n=240)	28.7% (n=240)	28.7% (n=240)
gpt-6-luna	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	99.2% (n=120)	99.2% (n=120)
gpt-6-luna	1	240	240	75.7% (n=240)	75.7% (n=240)	25.4% (n=240)	25.4% (n=240)	25.4% (n=240)	25.4% (n=240)
gpt-6-luna	2	240	240	77.9% (n=240)	77.9% (n=240)	30.8% (n=240)	30.8% (n=240)	30.8% (n=240)	30.8% (n=240)
claude-sonnet-5	0	120	120	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)	93.3% (n=120)
claude-sonnet-5	1	240	162	59.7% (n=240)	88.4% (n=162)	28.3% (n=240)	42.0% (n=162)	28.3% (n=240)	42.0% (n=162)
claude-sonnet-5	2	240	163	61.0% (n=240)	89.8% (n=163)	29.6% (n=240)	43.6% (n=163)	29.6% (n=240)	43.6% (n=163)
gpt-5.6-luna	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	98.3% (n=120)	98.3% (n=120)
gpt-5.6-luna	1	240	240	75.0% (n=240)	75.0% (n=240)	25.0% (n=240)	25.0% (n=240)	23.8% (n=240)	23.8% (n=240)
gpt-5.6-luna	2	240	240	78.5% (n=240)	78.5% (n=240)	31.7% (n=240)	31.7% (n=240)	31.2% (n=240)	31.2% (n=240)
claude-opus-5.5	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
claude-opus-5.5	1	240	237	90.4% (n=240)	91.6% (n=237)	27.1% (n=240)	27.4% (n=237)	26.7% (n=240)	27.0% (n=237)
claude-opus-5.5	2	240	234	89.3% (n=240)	91.5% (n=234)	22.9% (n=240)	23.5% (n=234)	22.9% (n=240)	23.5% (n=234)
claude-fable-5	0	120	89	74.2% (n=120)	100.0% (n=89)	74.2% (n=120)	100.0% (n=89)	74.2% (n=120)	100.0% (n=89)
claude-fable-5	1	240	151	59.5% (n=240)	94.5% (n=151)	33.3% (n=240)	53.0% (n=151)	33.3% (n=240)	53.0% (n=151)
claude-fable-5	2	240	153	59.8% (n=240)	93.8% (n=153)	28.3% (n=240)	44.4% (n=153)	28.3% (n=240)	44.4% (n=153)
mimo-v2.6-flash	0	120	120	96.3% (n=120)	96.3% (n=120)	95.0% (n=120)	95.0% (n=120)	91.7% (n=120)	91.7% (n=120)
mimo-v2.6-flash	1	240	236	75.6% (n=240)	76.8% (n=236)	28.7% (n=240)	29.2% (n=236)	26.7% (n=240)	27.1% (n=236)
mimo-v2.6-flash	2	240	238	72.6% (n=240)	73.2% (n=238)	25.0% (n=240)	25.2% (n=238)	24.6% (n=240)	24.8% (n=238)
mimo-v2.6-pro	0	120	120	97.3% (n=120)	97.3% (n=120)	94.2% (n=120)	94.2% (n=120)	92.5% (n=120)	92.5% (n=120)
mimo-v2.6-pro	1	240	236	70.6% (n=240)	70.6% (n=240)	25.8% (n=240)	25.8% (n=240)	24.6% (n=240)	24.6% (n=240)
mimo-v2.6-pro	2	240	237	72.2% (n=240)	72.2% (n=240)	25.0% (n=240)	25.0% (n=240)	24.2% (n=240)	24.2% (n=240)
claude-opus-5	0	120	0	0.0% (n=120)	— (n=0)	0.0% (n=120)	— (n=0)	0.0% (n=120)	— (n=0)
claude-opus-5	1	240	215	71.0% (n=240)	79.2% (n=215)	46.2% (n=240)	51.6% (n=215)	46.2% (n=240)	51.6% (n=215)
claude-opus-5	2	240	209	72.3% (n=240)	83.0% (n=209)	46.7% (n=240)	53.6% (n=209)	46.7% (n=240)	53.6% (n=209)
grok-4.6	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
grok-4.6	1	240	240	86.5% (n=240)	86.5% (n=240)	22.9% (n=240)	22.9% (n=240)	22.9% (n=240)	22.9% (n=240)
grok-4.6	2	240	240	87.1% (n=240)	87.1% (n=240)	19.6% (n=240)	19.6% (n=240)	19.6% (n=240)	19.6% (n=240)
kimi-k2.6	0	120	120	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)	100.0% (n=120)
kimi-k2.6	1	240	240	88.2% (n=240)	88.2% (n=240)	20.4% (n=240)	20.4% (n=240)	20.4% (n=240)	20.4% (n=240)
kimi-k2.6	2	240	239	87.8% (n=240)	88.2% (n=239)	20.8% (n=240)	20.9% (n=239)	20.8% (n=240)	20.9% (n=239)
minimax-m3	0	120	120	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)	97.5% (n=120)
minimax-m3	1	240	239	59.4% (n=240)	59.4% (n=240)	16.2% (n=240)	16.2% (n=240)	16.2% (n=240)	16.2% (n=240)
minimax-m3	2	240	238	63.0% (n=240)	63.0% (n=240)	19.6% (n=240)	19.6% (n=240)	19.6% (n=240)	19.6% (n=240)
qwen3.8-27b	0	120	120	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)	95.8% (n=120)
qwen3.8-27b	1	240	240	82.3% (n=240)	82.3% (n=240)	18.8% (n=240)	18.8% (n=240)	18.8% (n=240)	18.8% (n=240)
qwen3.8-27b	2	240	240	78.8% (n=240)	78.8% (n=240)	17.5% (n=240)	17.5% (n=240)	17.5% (n=240)	17.5% (n=240)
kimi-k3	0	120	93	77.5% (n=120)	100.0% (n=93)	77.5% (n=120)	100.0% (n=93)	77.5% (n=120)	100.0% (n=93)
kimi-k3	1	240	175	58.2% (n=240)	79.9% (n=175)	19.2% (n=240)	26.3% (n=175)	19.2% (n=240)	26.3% (n=175)
kimi-k3	2	240	175	60.0% (n=240)	82.2% (n=175)	20.0% (n=240)	27.4% (n=175)	20.0% (n=240)	27.4% (n=175)
glm-5.3-flash	0	120	120	99.0% (n=120)	99.0% (n=120)	83.3% (n=120)	83.3% (n=120)	83.3% (n=120)	83.3% (n=120)
glm-5.3-flash	1	240	239	60.6% (n=240)	60.8% (n=239)	11.2% (n=240)	11.3% (n=239)	10.8% (n=240)	10.9% (n=239)
glm-5.3-flash	2	240	237	56.6% (n=240)	57.3% (n=237)	12.1% (n=240)	12.2% (n=237)	12.1% (n=240)	12.2% (n=237)
claude-haiku-4.5	0	120	120	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)	98.3% (n=120)
claude-haiku-4.5	1	240	240	60.1% (n=240)	60.1% (n=240)	3.3% (n=240)	3.3% (n=240)	3.3% (n=240)	3.3% (n=240)
claude-haiku-4.5	2	240	240	60.8% (n=240)	60.8% (n=240)	6.7% (n=240)	6.7% (n=240)	6.7% (n=240)	6.7% (n=240)
glm-4.7-flash	0	120	120	90.4% (n=120)	90.4% (n=120)	77.5% (n=120)	77.5% (n=120)	77.5% (n=120)	77.5% (n=120)
glm-4.7-flash	1	240	220	56.5% (n=240)	61.4% (n=221)	4.2% (n=240)	4.5% (n=221)	4.2% (n=240)	4.5% (n=221)
glm-4.7-flash	2	240	225	56.5% (n=240)	60.3% (n=225)	5.8% (n=240)	6.2% (n=225)	5.8% (n=240)	6.2% (n=225)
claude-fable-5.1	0	120	3	2.5% (n=120)	100.0% (n=3)	2.5% (n=120)	100.0% (n=3)	2.5% (n=120)	100.0% (n=3)
claude-fable-5.1	1	240	7	2.8% (n=240)	96.5% (n=7)	1.2% (n=240)	42.9% (n=7)	1.2% (n=240)	42.9% (n=7)
claude-fable-5.1	2	240	4	1.7% (n=240)	100.0% (n=4)	1.7% (n=240)	100.0% (n=4)	1.7% (n=240)	100.0% (n=4)
baseline:direct-facts	0	120	120	73.7% (n=120)	73.7% (n=120)	0.8% (n=120)	0.8% (n=120)	0.8% (n=120)	0.8% (n=120)
baseline:direct-facts	1	240	240	73.7% (n=240)	73.7% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)
baseline:direct-facts	2	240	240	73.7% (n=240)	73.7% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)	0.8% (n=240)
baseline:story-copy	0	120	120	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)	0.0% (n=120)
baseline:story-copy	1	240	240	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)
baseline:story-copy	2	240	240	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)	0.0% (n=240)

genre
Provider	genre	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	hotel	110	110	100.0% (n=110)	100.0% (n=110)	100.0% (n=110)	100.0% (n=110)	100.0% (n=110)	100.0% (n=110)
baseline:constraint-solver	manor	105	105	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)
baseline:constraint-solver	maritime	90	90	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)
baseline:constraint-solver	observatory	125	125	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)
baseline:constraint-solver	theater	170	170	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)
baseline:forward-chain	hotel	110	110	99.2% (n=110)	99.2% (n=110)	90.9% (n=110)	90.9% (n=110)	90.9% (n=110)	90.9% (n=110)
baseline:forward-chain	manor	105	105	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)	100.0% (n=105)
baseline:forward-chain	maritime	90	90	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)	100.0% (n=90)
baseline:forward-chain	observatory	125	125	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)	100.0% (n=125)
baseline:forward-chain	theater	170	170	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)	100.0% (n=170)
gpt-6-astra	hotel	110	104	93.3% (n=110)	98.7% (n=104)	83.6% (n=110)	88.5% (n=104)	83.6% (n=110)	88.5% (n=104)
gpt-6-astra	manor	105	95	89.4% (n=105)	98.9% (n=95)	79.0% (n=105)	87.4% (n=95)	79.0% (n=105)	87.4% (n=95)
gpt-6-astra	maritime	90	85	93.0% (n=90)	98.5% (n=85)	78.9% (n=90)	83.5% (n=85)	78.9% (n=90)	83.5% (n=85)
gpt-6-astra	observatory	125	114	90.5% (n=125)	99.2% (n=114)	83.2% (n=125)	91.2% (n=114)	83.2% (n=125)	91.2% (n=114)
gpt-6-astra	theater	170	152	88.2% (n=170)	98.6% (n=152)	77.6% (n=170)	86.8% (n=152)	77.6% (n=170)	86.8% (n=152)
gpt-6-sol	hotel	110	110	96.0% (n=110)	96.0% (n=110)	74.5% (n=110)	74.5% (n=110)	74.5% (n=110)	74.5% (n=110)
gpt-6-sol	manor	105	105	95.6% (n=105)	95.6% (n=105)	71.4% (n=105)	71.4% (n=105)	71.4% (n=105)	71.4% (n=105)
gpt-6-sol	maritime	90	90	96.5% (n=90)	96.5% (n=90)	68.9% (n=90)	68.9% (n=90)	67.8% (n=90)	67.8% (n=90)
gpt-6-sol	observatory	125	125	97.1% (n=125)	97.1% (n=125)	77.6% (n=125)	77.6% (n=125)	77.6% (n=125)	77.6% (n=125)
gpt-6-sol	theater	170	170	97.4% (n=170)	97.4% (n=170)	76.5% (n=170)	76.5% (n=170)	76.5% (n=170)	76.5% (n=170)
gemini-3.7-flash	hotel	110	110	89.5% (n=110)	89.5% (n=110)	66.4% (n=110)	66.4% (n=110)	66.4% (n=110)	66.4% (n=110)
gemini-3.7-flash	manor	105	105	92.8% (n=105)	92.8% (n=105)	69.5% (n=105)	69.5% (n=105)	69.5% (n=105)	69.5% (n=105)
gemini-3.7-flash	maritime	90	90	89.7% (n=90)	89.7% (n=90)	63.3% (n=90)	63.3% (n=90)	63.3% (n=90)	63.3% (n=90)
gemini-3.7-flash	observatory	125	125	91.7% (n=125)	91.7% (n=125)	67.2% (n=125)	67.2% (n=125)	67.2% (n=125)	67.2% (n=125)
gemini-3.7-flash	theater	170	170	92.1% (n=170)	92.1% (n=170)	73.5% (n=170)	73.5% (n=170)	73.5% (n=170)	73.5% (n=170)
gpt-5.6-sol	hotel	110	110	92.3% (n=110)	92.3% (n=110)	76.4% (n=110)	76.4% (n=110)	76.4% (n=110)	76.4% (n=110)
gpt-5.6-sol	manor	105	105	90.0% (n=105)	90.0% (n=105)	65.7% (n=105)	65.7% (n=105)	65.7% (n=105)	65.7% (n=105)
gpt-5.6-sol	maritime	90	90	87.8% (n=90)	87.8% (n=90)	50.0% (n=90)	50.0% (n=90)	50.0% (n=90)	50.0% (n=90)
gpt-5.6-sol	observatory	125	125	90.2% (n=125)	90.2% (n=125)	75.2% (n=125)	75.2% (n=125)	75.2% (n=125)	75.2% (n=125)
gpt-5.6-sol	theater	170	170	93.1% (n=170)	93.1% (n=170)	70.0% (n=170)	70.0% (n=170)	70.0% (n=170)	70.0% (n=170)
gemini-3.8-flash	hotel	110	109	85.2% (n=110)	85.9% (n=109)	57.3% (n=110)	57.8% (n=109)	57.3% (n=110)	57.8% (n=109)
gemini-3.8-flash	manor	105	104	88.5% (n=105)	89.4% (n=104)	61.0% (n=105)	61.5% (n=104)	61.0% (n=105)	61.5% (n=104)
gemini-3.8-flash	maritime	90	90	86.7% (n=90)	86.7% (n=90)	61.1% (n=90)	61.1% (n=90)	61.1% (n=90)	61.1% (n=90)
gemini-3.8-flash	observatory	125	125	85.1% (n=125)	85.1% (n=125)	56.8% (n=125)	56.8% (n=125)	56.8% (n=125)	56.8% (n=125)
gemini-3.8-flash	theater	170	170	86.1% (n=170)	86.1% (n=170)	59.4% (n=170)	59.4% (n=170)	59.4% (n=170)	59.4% (n=170)
glm-5.3	hotel	110	106	81.8% (n=110)	84.9% (n=106)	52.7% (n=110)	54.7% (n=106)	52.7% (n=110)	54.7% (n=106)
glm-5.3	manor	105	100	78.6% (n=105)	82.6% (n=100)	54.3% (n=105)	57.0% (n=100)	53.3% (n=105)	56.0% (n=100)
glm-5.3	maritime	90	83	79.3% (n=90)	86.0% (n=83)	47.8% (n=90)	51.8% (n=83)	47.8% (n=90)	51.8% (n=83)
glm-5.3	observatory	125	116	77.6% (n=125)	83.6% (n=116)	54.4% (n=125)	58.6% (n=116)	54.4% (n=125)	58.6% (n=116)
glm-5.3	theater	170	158	82.1% (n=170)	87.8% (n=159)	55.3% (n=170)	59.1% (n=159)	55.3% (n=170)	59.1% (n=159)
gpt-5.6-terra	hotel	110	110	80.3% (n=110)	80.3% (n=110)	50.0% (n=110)	50.0% (n=110)	50.0% (n=110)	50.0% (n=110)
gpt-5.6-terra	manor	105	105	82.6% (n=105)	82.6% (n=105)	52.4% (n=105)	52.4% (n=105)	52.4% (n=105)	52.4% (n=105)
gpt-5.6-terra	maritime	90	90	80.0% (n=90)	80.0% (n=90)	44.4% (n=90)	44.4% (n=90)	44.4% (n=90)	44.4% (n=90)
gpt-5.6-terra	observatory	125	125	82.8% (n=125)	82.8% (n=125)	54.4% (n=125)	54.4% (n=125)	54.4% (n=125)	54.4% (n=125)
gpt-5.6-terra	theater	170	170	82.4% (n=170)	82.4% (n=170)	50.6% (n=170)	50.6% (n=170)	50.6% (n=170)	50.6% (n=170)
deepseek-4.1-flash	hotel	110	108	80.9% (n=110)	82.4% (n=108)	48.2% (n=110)	49.1% (n=108)	48.2% (n=110)	49.1% (n=108)
deepseek-4.1-flash	manor	105	105	80.9% (n=105)	80.9% (n=105)	55.2% (n=105)	55.2% (n=105)	55.2% (n=105)	55.2% (n=105)
deepseek-4.1-flash	maritime	90	90	83.1% (n=90)	83.1% (n=90)	46.7% (n=90)	46.7% (n=90)	46.7% (n=90)	46.7% (n=90)
deepseek-4.1-flash	observatory	125	125	73.0% (n=125)	73.0% (n=125)	46.4% (n=125)	46.4% (n=125)	46.4% (n=125)	46.4% (n=125)
deepseek-4.1-flash	theater	170	167	77.8% (n=170)	79.2% (n=167)	47.6% (n=170)	48.5% (n=167)	47.6% (n=170)	48.5% (n=167)
gemini-3.6-flash	hotel	110	110	80.7% (n=110)	80.7% (n=110)	44.5% (n=110)	44.5% (n=110)	44.5% (n=110)	44.5% (n=110)
gemini-3.6-flash	manor	105	105	80.6% (n=105)	80.6% (n=105)	42.9% (n=105)	42.9% (n=105)	42.9% (n=105)	42.9% (n=105)
gemini-3.6-flash	maritime	90	90	79.6% (n=90)	79.6% (n=90)	41.1% (n=90)	41.1% (n=90)	41.1% (n=90)	41.1% (n=90)
gemini-3.6-flash	observatory	125	125	80.6% (n=125)	80.6% (n=125)	45.6% (n=125)	45.6% (n=125)	45.6% (n=125)	45.6% (n=125)
gemini-3.6-flash	theater	170	170	77.2% (n=170)	77.2% (n=170)	43.5% (n=170)	43.5% (n=170)	43.5% (n=170)	43.5% (n=170)
deepseek-v4-pro	hotel	110	110	94.3% (n=110)	94.3% (n=110)	42.7% (n=110)	42.7% (n=110)	42.7% (n=110)	42.7% (n=110)
deepseek-v4-pro	manor	105	105	94.1% (n=105)	94.1% (n=105)	52.4% (n=105)	52.4% (n=105)	52.4% (n=105)	52.4% (n=105)
deepseek-v4-pro	maritime	90	90	88.7% (n=90)	88.7% (n=90)	34.4% (n=90)	34.4% (n=90)	34.4% (n=90)	34.4% (n=90)
deepseek-v4-pro	observatory	125	125	92.2% (n=125)	92.2% (n=125)	44.8% (n=125)	44.8% (n=125)	44.8% (n=125)	44.8% (n=125)
deepseek-v4-pro	theater	170	168	89.0% (n=170)	89.0% (n=170)	39.4% (n=170)	39.4% (n=170)	39.4% (n=170)	39.4% (n=170)
gpt-6-luna	hotel	110	110	78.1% (n=110)	78.1% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)
gpt-6-luna	manor	105	105	82.4% (n=105)	82.4% (n=105)	49.5% (n=105)	49.5% (n=105)	48.6% (n=105)	48.6% (n=105)
gpt-6-luna	maritime	90	90	77.8% (n=90)	77.8% (n=90)	31.1% (n=90)	31.1% (n=90)	31.1% (n=90)	31.1% (n=90)
gpt-6-luna	observatory	125	125	85.0% (n=125)	85.0% (n=125)	49.6% (n=125)	49.6% (n=125)	49.6% (n=125)	49.6% (n=125)
gpt-6-luna	theater	170	170	82.4% (n=170)	82.4% (n=170)	43.5% (n=170)	43.5% (n=170)	43.5% (n=170)	43.5% (n=170)
claude-sonnet-5	hotel	110	106	85.8% (n=110)	89.1% (n=106)	49.1% (n=110)	50.9% (n=106)	49.1% (n=110)	50.9% (n=106)
claude-sonnet-5	manor	105	62	54.2% (n=105)	91.8% (n=62)	40.0% (n=105)	67.7% (n=62)	40.0% (n=105)	67.7% (n=62)
claude-sonnet-5	maritime	90	53	54.9% (n=90)	93.3% (n=53)	33.3% (n=90)	56.6% (n=53)	33.3% (n=90)	56.6% (n=53)
claude-sonnet-5	observatory	125	59	44.0% (n=125)	93.2% (n=59)	32.0% (n=125)	67.8% (n=59)	32.0% (n=125)	67.8% (n=59)
claude-sonnet-5	theater	170	165	85.8% (n=170)	88.4% (n=165)	50.0% (n=170)	51.5% (n=165)	50.0% (n=170)	51.5% (n=165)
gpt-5.6-luna	hotel	110	110	84.2% (n=110)	84.2% (n=110)	43.6% (n=110)	43.6% (n=110)	42.7% (n=110)	42.7% (n=110)
gpt-5.6-luna	manor	105	105	82.7% (n=105)	82.7% (n=105)	44.8% (n=105)	44.8% (n=105)	44.8% (n=105)	44.8% (n=105)
gpt-5.6-luna	maritime	90	90	79.5% (n=90)	79.5% (n=90)	26.7% (n=90)	26.7% (n=90)	26.7% (n=90)	26.7% (n=90)
gpt-5.6-luna	observatory	125	125	79.7% (n=125)	79.7% (n=125)	48.8% (n=125)	48.8% (n=125)	47.2% (n=125)	47.2% (n=125)
gpt-5.6-luna	theater	170	170	80.9% (n=170)	80.9% (n=170)	44.7% (n=170)	44.7% (n=170)	42.9% (n=170)	42.9% (n=170)
claude-opus-5.5	hotel	110	110	93.2% (n=110)	93.2% (n=110)	40.0% (n=110)	40.0% (n=110)	40.0% (n=110)	40.0% (n=110)
claude-opus-5.5	manor	105	105	94.5% (n=105)	94.5% (n=105)	41.0% (n=105)	41.0% (n=105)	41.0% (n=105)	41.0% (n=105)
claude-opus-5.5	maritime	90	88	91.6% (n=90)	93.7% (n=88)	41.1% (n=90)	42.0% (n=88)	41.1% (n=90)	42.0% (n=88)
claude-opus-5.5	observatory	125	121	89.5% (n=125)	92.4% (n=121)	42.4% (n=125)	43.8% (n=121)	42.4% (n=125)	43.8% (n=121)
claude-opus-5.5	theater	170	167	91.3% (n=170)	92.9% (n=167)	37.1% (n=170)	37.7% (n=167)	36.5% (n=170)	37.1% (n=167)
claude-fable-5	hotel	110	59	51.1% (n=110)	95.3% (n=59)	29.1% (n=110)	54.2% (n=59)	29.1% (n=110)	54.2% (n=59)
claude-fable-5	manor	105	70	64.1% (n=105)	96.2% (n=70)	42.9% (n=105)	64.3% (n=70)	42.9% (n=105)	64.3% (n=70)
claude-fable-5	maritime	90	67	71.5% (n=90)	96.0% (n=67)	46.7% (n=90)	62.7% (n=67)	46.7% (n=90)	62.7% (n=67)
claude-fable-5	observatory	125	109	81.8% (n=125)	93.8% (n=109)	50.4% (n=125)	57.8% (n=109)	50.4% (n=125)	57.8% (n=109)
claude-fable-5	theater	170	88	50.0% (n=170)	96.7% (n=88)	32.4% (n=170)	62.5% (n=88)	32.4% (n=170)	62.5% (n=88)
mimo-v2.6-flash	hotel	110	108	78.8% (n=110)	80.2% (n=108)	42.7% (n=110)	43.5% (n=108)	41.8% (n=110)	42.6% (n=108)
mimo-v2.6-flash	manor	105	104	83.0% (n=105)	83.8% (n=104)	45.7% (n=105)	46.2% (n=104)	43.8% (n=105)	44.2% (n=104)
mimo-v2.6-flash	maritime	90	89	78.3% (n=90)	79.2% (n=89)	38.9% (n=90)	39.3% (n=89)	38.9% (n=90)	39.3% (n=89)
mimo-v2.6-flash	observatory	125	125	77.0% (n=125)	77.0% (n=125)	36.8% (n=125)	36.8% (n=125)	35.2% (n=125)	35.2% (n=125)
mimo-v2.6-flash	theater	170	168	76.8% (n=170)	77.7% (n=168)	39.4% (n=170)	39.9% (n=168)	36.5% (n=170)	36.9% (n=168)
mimo-v2.6-pro	hotel	110	110	80.0% (n=110)	80.0% (n=110)	41.8% (n=110)	41.8% (n=110)	41.8% (n=110)	41.8% (n=110)
mimo-v2.6-pro	manor	105	105	83.0% (n=105)	83.0% (n=105)	44.8% (n=105)	44.8% (n=105)	41.9% (n=105)	41.9% (n=105)
mimo-v2.6-pro	maritime	90	87	77.5% (n=90)	77.5% (n=90)	36.7% (n=90)	36.7% (n=90)	36.7% (n=90)	36.7% (n=90)
mimo-v2.6-pro	observatory	125	122	71.9% (n=125)	71.9% (n=125)	40.8% (n=125)	40.8% (n=125)	40.0% (n=125)	40.0% (n=125)
mimo-v2.6-pro	theater	170	169	73.4% (n=170)	73.4% (n=170)	34.1% (n=170)	34.1% (n=170)	32.4% (n=170)	32.4% (n=170)
claude-opus-5	hotel	110	85	65.5% (n=110)	84.7% (n=85)	49.1% (n=110)	63.5% (n=85)	49.1% (n=110)	63.5% (n=85)
claude-opus-5	manor	105	67	47.5% (n=105)	74.4% (n=67)	29.5% (n=105)	46.3% (n=67)	29.5% (n=105)	46.3% (n=67)
claude-opus-5	maritime	90	70	63.7% (n=90)	81.9% (n=70)	33.3% (n=90)	42.9% (n=70)	33.3% (n=90)	42.9% (n=70)
claude-opus-5	observatory	125	72	47.1% (n=125)	81.8% (n=72)	34.4% (n=125)	59.7% (n=72)	34.4% (n=125)	59.7% (n=72)
claude-opus-5	theater	170	130	62.2% (n=170)	81.3% (n=130)	38.2% (n=170)	50.0% (n=130)	38.2% (n=170)	50.0% (n=130)
grok-4.6	hotel	110	110	89.9% (n=110)	89.9% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)
grok-4.6	manor	105	105	89.3% (n=105)	89.3% (n=105)	34.3% (n=105)	34.3% (n=105)	34.3% (n=105)	34.3% (n=105)
grok-4.6	maritime	90	90	90.0% (n=90)	90.0% (n=90)	43.3% (n=90)	43.3% (n=90)	43.3% (n=90)	43.3% (n=90)
grok-4.6	observatory	125	125	89.6% (n=125)	89.6% (n=125)	35.2% (n=125)	35.2% (n=125)	35.2% (n=125)	35.2% (n=125)
grok-4.6	theater	170	170	88.9% (n=170)	88.9% (n=170)	37.6% (n=170)	37.6% (n=170)	37.6% (n=170)	37.6% (n=170)
kimi-k2.6	hotel	110	110	90.5% (n=110)	90.5% (n=110)	34.5% (n=110)	34.5% (n=110)	34.5% (n=110)	34.5% (n=110)
kimi-k2.6	manor	105	105	91.2% (n=105)	91.2% (n=105)	39.0% (n=105)	39.0% (n=105)	39.0% (n=105)	39.0% (n=105)
kimi-k2.6	maritime	90	90	93.0% (n=90)	93.0% (n=90)	40.0% (n=90)	40.0% (n=90)	40.0% (n=90)	40.0% (n=90)
kimi-k2.6	observatory	125	125	89.8% (n=125)	89.8% (n=125)	37.6% (n=125)	37.6% (n=125)	37.6% (n=125)	37.6% (n=125)
kimi-k2.6	theater	170	169	89.0% (n=170)	89.5% (n=169)	33.5% (n=170)	33.7% (n=169)	33.5% (n=170)	33.7% (n=169)
minimax-m3	hotel	110	109	68.3% (n=110)	68.3% (n=110)	37.3% (n=110)	37.3% (n=110)	37.3% (n=110)	37.3% (n=110)
minimax-m3	manor	105	105	72.7% (n=105)	72.7% (n=105)	38.1% (n=105)	38.1% (n=105)	38.1% (n=105)	38.1% (n=105)
minimax-m3	maritime	90	90	63.2% (n=90)	63.2% (n=90)	25.6% (n=90)	25.6% (n=90)	25.6% (n=90)	25.6% (n=90)
minimax-m3	observatory	125	123	61.9% (n=125)	61.9% (n=125)	32.0% (n=125)	32.0% (n=125)	32.0% (n=125)	32.0% (n=125)
minimax-m3	theater	170	170	73.5% (n=170)	73.5% (n=170)	34.7% (n=170)	34.7% (n=170)	34.7% (n=170)	34.7% (n=170)
qwen3.8-27b	hotel	110	110	84.0% (n=110)	84.0% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)	35.5% (n=110)
qwen3.8-27b	manor	105	105	85.7% (n=105)	85.7% (n=105)	33.3% (n=105)	33.3% (n=105)	33.3% (n=105)	33.3% (n=105)
qwen3.8-27b	maritime	90	90	83.7% (n=90)	83.7% (n=90)	31.1% (n=90)	31.1% (n=90)	31.1% (n=90)	31.1% (n=90)
qwen3.8-27b	observatory	125	125	82.6% (n=125)	82.6% (n=125)	32.0% (n=125)	32.0% (n=125)	32.0% (n=125)	32.0% (n=125)
qwen3.8-27b	theater	170	170	82.8% (n=170)	82.8% (n=170)	35.3% (n=170)	35.3% (n=170)	35.3% (n=170)	35.3% (n=170)
kimi-k3	hotel	110	93	70.5% (n=110)	83.4% (n=93)	36.4% (n=110)	43.0% (n=93)	36.4% (n=110)	43.0% (n=93)
kimi-k3	manor	105	76	63.4% (n=105)	87.6% (n=76)	34.3% (n=105)	47.4% (n=76)	34.3% (n=105)	47.4% (n=76)
kimi-k3	maritime	90	61	59.6% (n=90)	87.9% (n=61)	23.3% (n=90)	34.4% (n=61)	23.3% (n=90)	34.4% (n=61)
kimi-k3	observatory	125	95	60.6% (n=125)	79.7% (n=95)	32.0% (n=125)	42.1% (n=95)	32.0% (n=125)	42.1% (n=95)
kimi-k3	theater	170	118	60.7% (n=170)	87.5% (n=118)	29.4% (n=170)	42.4% (n=118)	29.4% (n=170)	42.4% (n=118)
glm-5.3-flash	hotel	110	110	68.3% (n=110)	68.3% (n=110)	25.5% (n=110)	25.5% (n=110)	25.5% (n=110)	25.5% (n=110)
glm-5.3-flash	manor	105	105	70.8% (n=105)	70.8% (n=105)	35.2% (n=105)	35.2% (n=105)	35.2% (n=105)	35.2% (n=105)
glm-5.3-flash	maritime	90	89	66.5% (n=90)	67.3% (n=89)	21.1% (n=90)	21.3% (n=89)	21.1% (n=90)	21.3% (n=89)
glm-5.3-flash	observatory	125	125	65.0% (n=125)	65.0% (n=125)	25.6% (n=125)	25.6% (n=125)	25.6% (n=125)	25.6% (n=125)
glm-5.3-flash	theater	170	167	64.4% (n=170)	65.5% (n=167)	23.5% (n=170)	24.0% (n=167)	22.9% (n=170)	23.4% (n=167)
claude-haiku-4.5	hotel	110	110	68.4% (n=110)	68.4% (n=110)	25.5% (n=110)	25.5% (n=110)	25.5% (n=110)	25.5% (n=110)
claude-haiku-4.5	manor	105	105	75.4% (n=105)	75.4% (n=105)	28.6% (n=105)	28.6% (n=105)	28.6% (n=105)	28.6% (n=105)
claude-haiku-4.5	maritime	90	90	70.3% (n=90)	70.3% (n=90)	23.3% (n=90)	23.3% (n=90)	23.3% (n=90)	23.3% (n=90)
claude-haiku-4.5	observatory	125	125	60.7% (n=125)	60.7% (n=125)	20.0% (n=125)	20.0% (n=125)	20.0% (n=125)	20.0% (n=125)
claude-haiku-4.5	theater	170	170	67.5% (n=170)	67.5% (n=170)	22.4% (n=170)	22.4% (n=170)	22.4% (n=170)	22.4% (n=170)
glm-4.7-flash	hotel	110	95	56.2% (n=110)	65.1% (n=95)	18.2% (n=110)	21.1% (n=95)	18.2% (n=110)	21.1% (n=95)
glm-4.7-flash	manor	105	102	68.4% (n=105)	70.4% (n=102)	24.8% (n=105)	25.5% (n=102)	24.8% (n=105)	25.5% (n=102)
glm-4.7-flash	maritime	90	84	65.6% (n=90)	70.3% (n=84)	16.7% (n=90)	17.9% (n=84)	16.7% (n=90)	17.9% (n=84)
glm-4.7-flash	observatory	125	120	67.1% (n=125)	69.9% (n=120)	20.8% (n=125)	21.7% (n=120)	20.8% (n=125)	21.7% (n=120)
glm-4.7-flash	theater	170	164	60.7% (n=170)	62.5% (n=165)	17.6% (n=170)	18.2% (n=165)	17.6% (n=170)	18.2% (n=165)
claude-fable-5.1	hotel	110	1	0.8% (n=110)	90.9% (n=1)	0.0% (n=110)	0.0% (n=1)	0.0% (n=110)	0.0% (n=1)
claude-fable-5.1	manor	105	3	2.8% (n=105)	99.3% (n=3)	1.9% (n=105)	66.7% (n=3)	1.9% (n=105)	66.7% (n=3)
claude-fable-5.1	maritime	90	4	4.4% (n=90)	98.1% (n=4)	3.3% (n=90)	75.0% (n=4)	3.3% (n=90)	75.0% (n=4)
claude-fable-5.1	observatory	125	2	1.6% (n=125)	100.0% (n=2)	1.6% (n=125)	100.0% (n=2)	1.6% (n=125)	100.0% (n=2)
claude-fable-5.1	theater	170	4	2.3% (n=170)	98.6% (n=4)	1.8% (n=170)	75.0% (n=4)	1.8% (n=170)	75.0% (n=4)
baseline:direct-facts	hotel	110	110	74.6% (n=110)	74.6% (n=110)	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)
baseline:direct-facts	manor	105	105	73.4% (n=105)	73.4% (n=105)	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)
baseline:direct-facts	maritime	90	90	76.6% (n=90)	76.6% (n=90)	5.6% (n=90)	5.6% (n=90)	5.6% (n=90)	5.6% (n=90)
baseline:direct-facts	observatory	125	125	73.6% (n=125)	73.6% (n=125)	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)
baseline:direct-facts	theater	170	170	71.8% (n=170)	71.8% (n=170)	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)
baseline:story-copy	hotel	110	110	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)	0.0% (n=110)
baseline:story-copy	manor	105	105	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)	0.0% (n=105)
baseline:story-copy	maritime	90	90	0.0% (n=90)	0.0% (n=90)	0.0% (n=90)	0.0% (n=90)	0.0% (n=90)	0.0% (n=90)
baseline:story-copy	observatory	125	125	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)	0.0% (n=125)
baseline:story-copy	theater	170	170	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)	0.0% (n=170)

renderer
Provider	renderer	Expected	Answered	Fact F1 · all items	Fact F1 · scored only	Exact world · all items	Exact world · scored only	Task success · all items	Task success · scored only
baseline:constraint-solver	template	600	600	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)	100.0% (n=600)
baseline:forward-chain	template	600	600	99.8% (n=600)	99.8% (n=600)	98.3% (n=600)	98.3% (n=600)	98.3% (n=600)	98.3% (n=600)
gpt-6-astra	template	600	550	90.6% (n=600)	98.8% (n=550)	80.3% (n=600)	87.6% (n=550)	80.3% (n=600)	87.6% (n=550)
gpt-6-sol	template	600	600	96.6% (n=600)	96.6% (n=600)	74.3% (n=600)	74.3% (n=600)	74.2% (n=600)	74.2% (n=600)
gemini-3.7-flash	template	600	600	91.3% (n=600)	91.3% (n=600)	68.7% (n=600)	68.7% (n=600)	68.7% (n=600)	68.7% (n=600)
gpt-5.6-sol	template	600	600	91.0% (n=600)	91.0% (n=600)	68.5% (n=600)	68.5% (n=600)	68.5% (n=600)	68.5% (n=600)
gemini-3.8-flash	template	600	598	86.2% (n=600)	86.5% (n=598)	59.0% (n=600)	59.2% (n=598)	59.0% (n=600)	59.2% (n=598)
glm-5.3	template	600	563	80.1% (n=600)	85.2% (n=564)	53.3% (n=600)	56.7% (n=564)	53.2% (n=600)	56.6% (n=564)
gpt-5.6-terra	template	600	600	81.8% (n=600)	81.8% (n=600)	50.7% (n=600)	50.7% (n=600)	50.7% (n=600)	50.7% (n=600)
deepseek-4.1-flash	template	600	595	78.7% (n=600)	79.4% (n=595)	48.7% (n=600)	49.1% (n=595)	48.7% (n=600)	49.1% (n=595)
gemini-3.6-flash	template	600	600	79.5% (n=600)	79.5% (n=600)	43.7% (n=600)	43.7% (n=600)	43.7% (n=600)	43.7% (n=600)
deepseek-v4-pro	template	600	598	91.5% (n=600)	91.5% (n=600)	42.7% (n=600)	42.7% (n=600)	42.7% (n=600)	42.7% (n=600)
gpt-6-luna	template	600	600	81.5% (n=600)	81.5% (n=600)	42.5% (n=600)	42.5% (n=600)	42.3% (n=600)	42.3% (n=600)
claude-sonnet-5	template	600	445	66.9% (n=600)	90.2% (n=445)	41.8% (n=600)	56.4% (n=445)	41.8% (n=600)	56.4% (n=445)
gpt-5.6-luna	template	600	600	81.4% (n=600)	81.4% (n=600)	42.7% (n=600)	42.7% (n=600)	41.7% (n=600)	41.7% (n=600)
claude-opus-5.5	template	600	591	91.9% (n=600)	93.3% (n=591)	40.0% (n=600)	40.6% (n=591)	39.8% (n=600)	40.4% (n=591)
claude-fable-5	template	600	393	62.5% (n=600)	95.5% (n=393)	39.5% (n=600)	60.3% (n=393)	39.5% (n=600)	60.3% (n=393)
mimo-v2.6-flash	template	600	594	78.5% (n=600)	79.3% (n=594)	40.5% (n=600)	40.9% (n=594)	38.8% (n=600)	39.2% (n=594)
mimo-v2.6-pro	template	600	593	76.6% (n=600)	76.6% (n=600)	39.2% (n=600)	39.2% (n=600)	38.0% (n=600)	38.0% (n=600)
claude-opus-5	template	600	424	57.3% (n=600)	81.1% (n=424)	37.2% (n=600)	52.6% (n=424)	37.2% (n=600)	52.6% (n=424)
grok-4.6	template	600	600	89.5% (n=600)	89.5% (n=600)	37.0% (n=600)	37.0% (n=600)	37.0% (n=600)	37.0% (n=600)
kimi-k2.6	template	600	599	90.4% (n=600)	90.6% (n=599)	36.5% (n=600)	36.6% (n=599)	36.5% (n=600)	36.6% (n=599)
minimax-m3	template	600	597	68.5% (n=600)	68.5% (n=600)	33.8% (n=600)	33.8% (n=600)	33.8% (n=600)	33.8% (n=600)
qwen3.8-27b	template	600	600	83.6% (n=600)	83.6% (n=600)	33.7% (n=600)	33.7% (n=600)	33.7% (n=600)	33.7% (n=600)
kimi-k3	template	600	443	62.8% (n=600)	85.0% (n=443)	31.2% (n=600)	42.2% (n=443)	31.2% (n=600)	42.2% (n=443)
glm-5.3-flash	template	600	596	66.7% (n=600)	67.1% (n=596)	26.0% (n=600)	26.2% (n=596)	25.8% (n=600)	26.0% (n=596)
claude-haiku-4.5	template	600	600	68.0% (n=600)	68.0% (n=600)	23.7% (n=600)	23.7% (n=600)	23.7% (n=600)	23.7% (n=600)
glm-4.7-flash	template	600	565	63.3% (n=600)	67.1% (n=566)	19.5% (n=600)	20.7% (n=566)	19.5% (n=600)	20.7% (n=566)
claude-fable-5.1	template	600	14	2.3% (n=600)	98.2% (n=14)	1.7% (n=600)	71.4% (n=14)	1.7% (n=600)	71.4% (n=14)
baseline:direct-facts	template	600	600	73.7% (n=600)	73.7% (n=600)	0.8% (n=600)	0.8% (n=600)	0.8% (n=600)	0.8% (n=600)
baseline:story-copy	template	600	600	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)	0.0% (n=600)

Model pairs · fact F1 difference (percentage points, left − right)

Differences are left minus right, in percentage points. Complete scored pairs only; condition pairs require all configured realizations on both sides. Missing pairs are excluded.

{
  "caution": "Descriptive intervals, not multiplicity-adjusted; few families give unstable uncertainty estimates.",
  "confidence": 0.95,
  "method": "family-cluster percentile bootstrap",
  "resamples": 2000,
  "seed": 0,
  "strata_intervals": false
}

models
Provider	Left	Right	Metric	Difference (pp)	95% CI (pp)	Expected pairs	Complete pairs	Missing pairs	Families
All providers	baseline:constraint-solver	baseline:direct-facts	fact_f1	26.3%	24.5% to 28.2%	600	600	0	120
All providers	baseline:constraint-solver	baseline:direct-facts	exact_world	99.2%	97.5% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	baseline:direct-facts	task_success	99.2%	97.5% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	baseline:direct-facts	decision_correct	65.8%	57.5% to 74.2%	600	600	0	120
All providers	baseline:constraint-solver	baseline:forward-chain	fact_f1	0.2%	0.0% to 0.4%	600	600	0	120
All providers	baseline:constraint-solver	baseline:forward-chain	exact_world	1.7%	0.0% to 4.2%	600	600	0	120
All providers	baseline:constraint-solver	baseline:forward-chain	task_success	1.7%	0.0% to 4.2%	600	600	0	120
All providers	baseline:constraint-solver	baseline:forward-chain	decision_correct	0.8%	0.0% to 2.5%	600	600	0	120
All providers	baseline:constraint-solver	baseline:story-copy	fact_f1	100.0%	100.0% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	baseline:story-copy	exact_world	100.0%	100.0% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	baseline:story-copy	task_success	100.0%	100.0% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	baseline:story-copy	decision_correct	100.0%	100.0% to 100.0%	600	600	0	120
All providers	baseline:constraint-solver	claude-fable-5	fact_f1	4.5%	3.6% to 5.5%	600	393	207	120
All providers	baseline:constraint-solver	claude-fable-5	exact_world	39.7%	34.0% to 45.2%	600	393	207	120
All providers	baseline:constraint-solver	claude-fable-5	task_success	39.7%	34.0% to 45.2%	600	393	207	120
All providers	baseline:constraint-solver	claude-fable-5	decision_correct	1.3%	0.2% to 2.7%	600	393	207	120
All providers	baseline:constraint-solver	claude-fable-5.1	fact_f1	1.8%	0.3% to 3.5%	600	14	586	13
All providers	baseline:constraint-solver	claude-fable-5.1	exact_world	28.6%	7.7% to 50.0%	600	14	586	13
All providers	baseline:constraint-solver	claude-fable-5.1	task_success	28.6%	7.7% to 50.0%	600	14	586	13
All providers	baseline:constraint-solver	claude-fable-5.1	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	baseline:constraint-solver	claude-haiku-4.5	fact_f1	32.0%	29.1% to 34.8%	600	600	0	120
All providers	baseline:constraint-solver	claude-haiku-4.5	exact_world	76.3%	74.3% to 78.2%	600	600	0	120
All providers	baseline:constraint-solver	claude-haiku-4.5	task_success	76.3%	74.3% to 78.2%	600	600	0	120
All providers	baseline:constraint-solver	claude-haiku-4.5	decision_correct	4.5%	2.7% to 6.5%	600	600	0	120
All providers	baseline:constraint-solver	claude-opus-5	fact_f1	18.9%	15.7% to 22.1%	600	424	176	119
All providers	baseline:constraint-solver	claude-opus-5	exact_world	47.4%	41.7% to 52.8%	600	424	176	119
All providers	baseline:constraint-solver	claude-opus-5	task_success	47.4%	41.7% to 52.8%	600	424	176	119
All providers	baseline:constraint-solver	claude-opus-5	decision_correct	8.5%	5.9% to 11.4%	600	424	176	119
All providers	baseline:constraint-solver	claude-opus-5.5	fact_f1	6.7%	5.9% to 7.6%	600	591	9	120
All providers	baseline:constraint-solver	claude-opus-5.5	exact_world	59.4%	55.7% to 62.8%	600	591	9	120
All providers	baseline:constraint-solver	claude-opus-5.5	task_success	59.6%	55.8% to 63.0%	600	591	9	120
All providers	baseline:constraint-solver	claude-opus-5.5	decision_correct	4.7%	2.9% to 6.9%	600	591	9	120
All providers	baseline:constraint-solver	claude-sonnet-5	fact_f1	9.8%	7.6% to 11.9%	600	445	155	120
All providers	baseline:constraint-solver	claude-sonnet-5	exact_world	43.6%	39.1% to 48.7%	600	445	155	120
All providers	baseline:constraint-solver	claude-sonnet-5	task_success	43.6%	39.1% to 48.7%	600	445	155	120
All providers	baseline:constraint-solver	claude-sonnet-5	decision_correct	4.0%	2.3% to 5.9%	600	445	155	120
All providers	baseline:constraint-solver	deepseek-4.1-flash	fact_f1	20.6%	18.3% to 22.9%	600	595	5	120
All providers	baseline:constraint-solver	deepseek-4.1-flash	exact_world	50.9%	46.9% to 55.1%	600	595	5	120
All providers	baseline:constraint-solver	deepseek-4.1-flash	task_success	50.9%	46.9% to 55.1%	600	595	5	120
All providers	baseline:constraint-solver	deepseek-4.1-flash	decision_correct	0.0%	0.0% to 0.0%	600	595	5	120
All providers	baseline:constraint-solver	deepseek-v4-pro	fact_f1	8.5%	7.3% to 9.8%	600	600	0	120
All providers	baseline:constraint-solver	deepseek-v4-pro	exact_world	57.3%	53.2% to 61.2%	600	600	0	120
All providers	baseline:constraint-solver	deepseek-v4-pro	task_success	57.3%	53.2% to 61.2%	600	600	0	120
All providers	baseline:constraint-solver	deepseek-v4-pro	decision_correct	4.7%	2.8% to 6.7%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.6-flash	fact_f1	20.5%	17.9% to 23.2%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.6-flash	exact_world	56.3%	52.2% to 60.7%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.6-flash	task_success	56.3%	52.2% to 60.7%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.6-flash	decision_correct	1.0%	0.2% to 2.2%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.7-flash	fact_f1	8.7%	7.0% to 10.5%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.7-flash	exact_world	31.3%	27.2% to 35.2%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.7-flash	task_success	31.3%	27.2% to 35.2%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.7-flash	decision_correct	0.5%	0.0% to 1.3%	600	600	0	120
All providers	baseline:constraint-solver	gemini-3.8-flash	fact_f1	13.5%	11.3% to 15.6%	600	598	2	120
All providers	baseline:constraint-solver	gemini-3.8-flash	exact_world	40.8%	36.4% to 45.0%	600	598	2	120
All providers	baseline:constraint-solver	gemini-3.8-flash	task_success	40.8%	36.4% to 45.0%	600	598	2	120
All providers	baseline:constraint-solver	gemini-3.8-flash	decision_correct	0.3%	0.0% to 0.8%	600	598	2	120
All providers	baseline:constraint-solver	glm-4.7-flash	fact_f1	32.9%	30.1% to 35.6%	600	566	34	120
All providers	baseline:constraint-solver	glm-4.7-flash	exact_world	79.3%	77.0% to 81.5%	600	566	34	120
All providers	baseline:constraint-solver	glm-4.7-flash	task_success	79.3%	77.0% to 81.5%	600	566	34	120
All providers	baseline:constraint-solver	glm-4.7-flash	decision_correct	17.5%	14.2% to 20.9%	600	566	34	120
All providers	baseline:constraint-solver	glm-5.3	fact_f1	14.8%	11.9% to 17.8%	600	564	36	120
All providers	baseline:constraint-solver	glm-5.3	exact_world	43.3%	38.5% to 47.8%	600	564	36	120
All providers	baseline:constraint-solver	glm-5.3	task_success	43.4%	38.6% to 47.9%	600	564	36	120
All providers	baseline:constraint-solver	glm-5.3	decision_correct	3.7%	2.3% to 5.4%	600	564	36	120
All providers	baseline:constraint-solver	glm-5.3-flash	fact_f1	32.9%	29.5% to 36.1%	600	596	4	120
All providers	baseline:constraint-solver	glm-5.3-flash	exact_world	73.8%	70.6% to 76.8%	600	596	4	120
All providers	baseline:constraint-solver	glm-5.3-flash	task_success	74.0%	70.7% to 77.0%	600	596	4	120
All providers	baseline:constraint-solver	glm-5.3-flash	decision_correct	1.7%	0.8% to 2.7%	600	596	4	120
All providers	baseline:constraint-solver	gpt-5.6-luna	fact_f1	18.6%	16.6% to 20.6%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-luna	exact_world	57.3%	54.0% to 60.7%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-luna	task_success	58.3%	55.0% to 61.7%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-luna	decision_correct	2.8%	1.5% to 4.3%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-sol	fact_f1	9.0%	7.2% to 10.7%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-sol	exact_world	31.5%	27.2% to 36.2%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-sol	task_success	31.5%	27.2% to 36.2%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-sol	decision_correct	0.0%	0.0% to 0.0%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-terra	fact_f1	18.2%	16.2% to 20.3%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-terra	exact_world	49.3%	45.7% to 53.0%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-terra	task_success	49.3%	45.7% to 53.0%	600	600	0	120
All providers	baseline:constraint-solver	gpt-5.6-terra	decision_correct	0.2%	0.0% to 0.5%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-astra	fact_f1	1.2%	0.8% to 1.7%	600	550	50	115
All providers	baseline:constraint-solver	gpt-6-astra	exact_world	12.4%	8.7% to 16.5%	600	550	50	115
All providers	baseline:constraint-solver	gpt-6-astra	task_success	12.4%	8.7% to 16.5%	600	550	50	115
All providers	baseline:constraint-solver	gpt-6-astra	decision_correct	0.0%	0.0% to 0.0%	600	550	50	115
All providers	baseline:constraint-solver	gpt-6-luna	fact_f1	18.5%	16.3% to 20.8%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-luna	exact_world	57.5%	53.7% to 61.0%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-luna	task_success	57.7%	54.0% to 61.2%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-luna	decision_correct	1.7%	0.7% to 2.7%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-sol	fact_f1	3.4%	2.6% to 4.2%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-sol	exact_world	25.7%	21.5% to 29.8%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-sol	task_success	25.8%	21.7% to 30.0%	600	600	0	120
All providers	baseline:constraint-solver	gpt-6-sol	decision_correct	1.5%	0.7% to 2.5%	600	600	0	120
All providers	baseline:constraint-solver	grok-4.6	fact_f1	10.5%	9.3% to 11.7%	600	600	0	120
All providers	baseline:constraint-solver	grok-4.6	exact_world	63.0%	59.2% to 66.5%	600	600	0	120
All providers	baseline:constraint-solver	grok-4.6	task_success	63.0%	59.2% to 66.5%	600	600	0	120
All providers	baseline:constraint-solver	grok-4.6	decision_correct	3.3%	1.3% to 5.5%	600	600	0	120
All providers	baseline:constraint-solver	kimi-k2.6	fact_f1	9.4%	8.3% to 10.7%	600	599	1	120
All providers	baseline:constraint-solver	kimi-k2.6	exact_world	63.4%	59.9% to 66.9%	600	599	1	120
All providers	baseline:constraint-solver	kimi-k2.6	task_success	63.4%	59.9% to 66.9%	600	599	1	120
All providers	baseline:constraint-solver	kimi-k2.6	decision_correct	2.2%	1.0% to 3.5%	600	599	1	120
All providers	baseline:constraint-solver	kimi-k3	fact_f1	15.0%	12.2% to 17.9%	600	443	157	96
All providers	baseline:constraint-solver	kimi-k3	exact_world	57.8%	53.0% to 62.4%	600	443	157	96
All providers	baseline:constraint-solver	kimi-k3	task_success	57.8%	53.0% to 62.4%	600	443	157	96
All providers	baseline:constraint-solver	kimi-k3	decision_correct	0.2%	0.0% to 0.7%	600	443	157	96
All providers	baseline:constraint-solver	mimo-v2.6-flash	fact_f1	20.7%	18.3% to 22.9%	600	594	6	120
All providers	baseline:constraint-solver	mimo-v2.6-flash	exact_world	59.1%	55.6% to 62.3%	600	594	6	120
All providers	baseline:constraint-solver	mimo-v2.6-flash	task_success	60.8%	57.2% to 64.0%	600	594	6	120
All providers	baseline:constraint-solver	mimo-v2.6-flash	decision_correct	10.1%	7.5% to 12.9%	600	594	6	120
All providers	baseline:constraint-solver	mimo-v2.6-pro	fact_f1	23.4%	20.9% to 26.0%	600	600	0	120
All providers	baseline:constraint-solver	mimo-v2.6-pro	exact_world	60.8%	57.3% to 64.3%	600	600	0	120
All providers	baseline:constraint-solver	mimo-v2.6-pro	task_success	62.0%	58.5% to 65.7%	600	600	0	120
All providers	baseline:constraint-solver	mimo-v2.6-pro	decision_correct	11.5%	8.8% to 14.3%	600	600	0	120
All providers	baseline:constraint-solver	minimax-m3	fact_f1	31.5%	28.3% to 34.7%	600	600	0	120
All providers	baseline:constraint-solver	minimax-m3	exact_world	66.2%	62.8% to 69.3%	600	600	0	120
All providers	baseline:constraint-solver	minimax-m3	task_success	66.2%	62.8% to 69.3%	600	600	0	120
All providers	baseline:constraint-solver	minimax-m3	decision_correct	3.3%	1.8% to 5.0%	600	600	0	120
All providers	baseline:constraint-solver	qwen3.8-27b	fact_f1	16.4%	14.3% to 18.7%	600	600	0	120
All providers	baseline:constraint-solver	qwen3.8-27b	exact_world	66.3%	62.5% to 69.8%	600	600	0	120
All providers	baseline:constraint-solver	qwen3.8-27b	task_success	66.3%	62.5% to 69.8%	600	600	0	120
All providers	baseline:constraint-solver	qwen3.8-27b	decision_correct	3.0%	1.5% to 4.8%	600	600	0	120
All providers	baseline:direct-facts	baseline:forward-chain	fact_f1	-26.2%	-28.0% to -24.3%	600	600	0	120
All providers	baseline:direct-facts	baseline:forward-chain	exact_world	-97.5%	-100.0% to -94.2%	600	600	0	120
All providers	baseline:direct-facts	baseline:forward-chain	task_success	-97.5%	-100.0% to -94.2%	600	600	0	120
All providers	baseline:direct-facts	baseline:forward-chain	decision_correct	-65.0%	-73.3% to -56.7%	600	600	0	120
All providers	baseline:direct-facts	baseline:story-copy	fact_f1	73.7%	71.8% to 75.5%	600	600	0	120
All providers	baseline:direct-facts	baseline:story-copy	exact_world	0.8%	0.0% to 2.5%	600	600	0	120
All providers	baseline:direct-facts	baseline:story-copy	task_success	0.8%	0.0% to 2.5%	600	600	0	120
All providers	baseline:direct-facts	baseline:story-copy	decision_correct	34.2%	25.8% to 42.5%	600	600	0	120
All providers	baseline:direct-facts	claude-fable-5	fact_f1	-21.4%	-23.6% to -19.2%	600	393	207	120
All providers	baseline:direct-facts	claude-fable-5	exact_world	-59.3%	-65.2% to -53.2%	600	393	207	120
All providers	baseline:direct-facts	claude-fable-5	task_success	-59.3%	-65.2% to -53.2%	600	393	207	120
All providers	baseline:direct-facts	claude-fable-5	decision_correct	-65.6%	-74.9% to -56.1%	600	393	207	120
All providers	baseline:direct-facts	claude-fable-5.1	fact_f1	-27.0%	-34.2% to -21.1%	600	14	586	13
All providers	baseline:direct-facts	claude-fable-5.1	exact_world	-71.4%	-92.3% to -50.0%	600	14	586	13
All providers	baseline:direct-facts	claude-fable-5.1	task_success	-71.4%	-92.3% to -50.0%	600	14	586	13
All providers	baseline:direct-facts	claude-fable-5.1	decision_correct	-64.3%	-92.3% to -37.5%	600	14	586	13
All providers	baseline:direct-facts	claude-haiku-4.5	fact_f1	5.6%	2.8% to 8.3%	600	600	0	120
All providers	baseline:direct-facts	claude-haiku-4.5	exact_world	-22.8%	-24.8% to -20.7%	600	600	0	120
All providers	baseline:direct-facts	claude-haiku-4.5	task_success	-22.8%	-24.8% to -20.7%	600	600	0	120
All providers	baseline:direct-facts	claude-haiku-4.5	decision_correct	-61.3%	-69.5% to -53.0%	600	600	0	120
All providers	baseline:direct-facts	claude-opus-5	fact_f1	-7.0%	-10.4% to -3.9%	600	424	176	119
All providers	baseline:direct-facts	claude-opus-5	exact_world	-51.7%	-57.3% to -46.1%	600	424	176	119
All providers	baseline:direct-facts	claude-opus-5	task_success	-51.7%	-57.3% to -46.1%	600	424	176	119
All providers	baseline:direct-facts	claude-opus-5	decision_correct	-58.5%	-67.5% to -49.4%	600	424	176	119
All providers	baseline:direct-facts	claude-opus-5.5	fact_f1	-19.5%	-21.7% to -17.5%	600	591	9	120
All providers	baseline:direct-facts	claude-opus-5.5	exact_world	-39.8%	-44.0% to -35.4%	600	591	9	120
All providers	baseline:direct-facts	claude-opus-5.5	task_success	-39.6%	-43.8% to -35.3%	600	591	9	120
All providers	baseline:direct-facts	claude-opus-5.5	decision_correct	-60.9%	-69.0% to -52.9%	600	591	9	120
All providers	baseline:direct-facts	claude-sonnet-5	fact_f1	-16.6%	-19.4% to -13.9%	600	445	155	120
All providers	baseline:direct-facts	claude-sonnet-5	exact_world	-55.3%	-60.3% to -49.7%	600	445	155	120
All providers	baseline:direct-facts	claude-sonnet-5	task_success	-55.3%	-60.3% to -49.7%	600	445	155	120
All providers	baseline:direct-facts	claude-sonnet-5	decision_correct	-65.2%	-74.0% to -56.8%	600	445	155	120
All providers	baseline:direct-facts	deepseek-4.1-flash	fact_f1	-5.6%	-8.3% to -2.8%	600	595	5	120
All providers	baseline:direct-facts	deepseek-4.1-flash	exact_world	-48.2%	-52.5% to -43.6%	600	595	5	120
All providers	baseline:direct-facts	deepseek-4.1-flash	task_success	-48.2%	-52.5% to -43.6%	600	595	5	120
All providers	baseline:direct-facts	deepseek-4.1-flash	decision_correct	-65.5%	-73.9% to -57.2%	600	595	5	120
All providers	baseline:direct-facts	deepseek-v4-pro	fact_f1	-17.8%	-19.8% to -15.7%	600	600	0	120
All providers	baseline:direct-facts	deepseek-v4-pro	exact_world	-41.8%	-46.3% to -37.5%	600	600	0	120
All providers	baseline:direct-facts	deepseek-v4-pro	task_success	-41.8%	-46.3% to -37.5%	600	600	0	120
All providers	baseline:direct-facts	deepseek-v4-pro	decision_correct	-61.2%	-69.2% to -52.8%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.6-flash	fact_f1	-5.8%	-8.7% to -2.9%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.6-flash	exact_world	-42.8%	-47.0% to -38.7%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.6-flash	task_success	-42.8%	-47.0% to -38.7%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.6-flash	decision_correct	-64.8%	-73.0% to -56.5%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.7-flash	fact_f1	-17.6%	-19.9% to -15.5%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.7-flash	exact_world	-67.8%	-72.2% to -63.8%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.7-flash	task_success	-67.8%	-72.2% to -63.8%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.7-flash	decision_correct	-65.3%	-73.5% to -57.2%	600	600	0	120
All providers	baseline:direct-facts	gemini-3.8-flash	fact_f1	-12.8%	-15.3% to -10.5%	600	598	2	120
All providers	baseline:direct-facts	gemini-3.8-flash	exact_world	-58.4%	-62.8% to -54.0%	600	598	2	120
All providers	baseline:direct-facts	gemini-3.8-flash	task_success	-58.4%	-62.8% to -54.0%	600	598	2	120
All providers	baseline:direct-facts	gemini-3.8-flash	decision_correct	-65.4%	-73.6% to -57.1%	600	598	2	120
All providers	baseline:direct-facts	glm-4.7-flash	fact_f1	6.9%	3.7% to 10.0%	600	566	34	120
All providers	baseline:direct-facts	glm-4.7-flash	exact_world	-19.8%	-22.5% to -16.9%	600	566	34	120
All providers	baseline:direct-facts	glm-4.7-flash	task_success	-19.8%	-22.5% to -16.9%	600	566	34	120
All providers	baseline:direct-facts	glm-4.7-flash	decision_correct	-46.5%	-55.5% to -37.3%	600	566	34	120
All providers	baseline:direct-facts	glm-5.3	fact_f1	-11.4%	-14.7% to -8.1%	600	564	36	120
All providers	baseline:direct-facts	glm-5.3	exact_world	-56.0%	-61.1% to -51.4%	600	564	36	120
All providers	baseline:direct-facts	glm-5.3	task_success	-55.9%	-61.0% to -51.3%	600	564	36	120
All providers	baseline:direct-facts	glm-5.3	decision_correct	-62.2%	-70.7% to -53.7%	600	564	36	120
All providers	baseline:direct-facts	glm-5.3-flash	fact_f1	6.6%	3.0% to 10.0%	600	596	4	120
All providers	baseline:direct-facts	glm-5.3-flash	exact_world	-25.5%	-29.1% to -22.1%	600	596	4	120
All providers	baseline:direct-facts	glm-5.3-flash	task_success	-25.3%	-28.9% to -22.0%	600	596	4	120
All providers	baseline:direct-facts	glm-5.3-flash	decision_correct	-64.3%	-72.7% to -55.8%	600	596	4	120
All providers	baseline:direct-facts	gpt-5.6-luna	fact_f1	-7.7%	-10.3% to -5.0%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-luna	exact_world	-41.8%	-45.7% to -38.0%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-luna	task_success	-40.8%	-44.7% to -37.0%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-luna	decision_correct	-63.0%	-71.2% to -54.7%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-sol	fact_f1	-17.3%	-19.9% to -14.7%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-sol	exact_world	-67.7%	-72.5% to -62.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-sol	task_success	-67.7%	-72.5% to -62.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-sol	decision_correct	-65.8%	-74.2% to -57.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-terra	fact_f1	-8.1%	-11.0% to -5.3%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-terra	exact_world	-49.8%	-54.0% to -45.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-terra	task_success	-49.8%	-54.0% to -45.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-5.6-terra	decision_correct	-65.7%	-74.0% to -57.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-astra	fact_f1	-24.6%	-26.7% to -22.5%	600	550	50	115
All providers	baseline:direct-facts	gpt-6-astra	exact_world	-86.7%	-91.2% to -81.7%	600	550	50	115
All providers	baseline:direct-facts	gpt-6-astra	task_success	-86.7%	-91.2% to -81.7%	600	550	50	115
All providers	baseline:direct-facts	gpt-6-astra	decision_correct	-66.0%	-74.7% to -57.1%	600	550	50	115
All providers	baseline:direct-facts	gpt-6-luna	fact_f1	-7.8%	-10.7% to -5.0%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-luna	exact_world	-41.7%	-45.8% to -37.7%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-luna	task_success	-41.5%	-45.5% to -37.5%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-luna	decision_correct	-64.2%	-72.3% to -55.7%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-sol	fact_f1	-23.0%	-25.2% to -20.8%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-sol	exact_world	-73.5%	-78.0% to -68.8%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-sol	task_success	-73.3%	-77.8% to -68.7%	600	600	0	120
All providers	baseline:direct-facts	gpt-6-sol	decision_correct	-64.3%	-72.7% to -56.0%	600	600	0	120
All providers	baseline:direct-facts	grok-4.6	fact_f1	-15.8%	-18.2% to -13.6%	600	600	0	120
All providers	baseline:direct-facts	grok-4.6	exact_world	-36.2%	-40.0% to -32.3%	600	600	0	120
All providers	baseline:direct-facts	grok-4.6	task_success	-36.2%	-40.0% to -32.3%	600	600	0	120
All providers	baseline:direct-facts	grok-4.6	decision_correct	-62.5%	-70.8% to -53.8%	600	600	0	120
All providers	baseline:direct-facts	kimi-k2.6	fact_f1	-16.9%	-18.9% to -14.8%	600	599	1	120
All providers	baseline:direct-facts	kimi-k2.6	exact_world	-35.7%	-39.3% to -32.2%	600	599	1	120
All providers	baseline:direct-facts	kimi-k2.6	task_success	-35.7%	-39.3% to -32.2%	600	599	1	120
All providers	baseline:direct-facts	kimi-k2.6	decision_correct	-63.8%	-72.2% to -55.2%	600	599	1	120
All providers	baseline:direct-facts	kimi-k3	fact_f1	-10.2%	-13.4% to -7.1%	600	443	157	96
All providers	baseline:direct-facts	kimi-k3	exact_world	-41.1%	-46.3% to -36.0%	600	443	157	96
All providers	baseline:direct-facts	kimi-k3	task_success	-41.1%	-46.3% to -36.0%	600	443	157	96
All providers	baseline:direct-facts	kimi-k3	decision_correct	-64.3%	-74.2% to -54.3%	600	443	157	96
All providers	baseline:direct-facts	mimo-v2.6-flash	fact_f1	-5.6%	-8.4% to -3.0%	600	594	6	120
All providers	baseline:direct-facts	mimo-v2.6-flash	exact_world	-40.1%	-43.8% to -36.4%	600	594	6	120
All providers	baseline:direct-facts	mimo-v2.6-flash	task_success	-38.4%	-42.1% to -34.8%	600	594	6	120
All providers	baseline:direct-facts	mimo-v2.6-flash	decision_correct	-55.4%	-63.9% to -46.3%	600	594	6	120
All providers	baseline:direct-facts	mimo-v2.6-pro	fact_f1	-2.9%	-5.9% to 0.1%	600	600	0	120
All providers	baseline:direct-facts	mimo-v2.6-pro	exact_world	-38.3%	-42.0% to -34.5%	600	600	0	120
All providers	baseline:direct-facts	mimo-v2.6-pro	task_success	-37.2%	-41.0% to -33.3%	600	600	0	120
All providers	baseline:direct-facts	mimo-v2.6-pro	decision_correct	-54.3%	-63.5% to -45.2%	600	600	0	120
All providers	baseline:direct-facts	minimax-m3	fact_f1	5.2%	1.9% to 8.6%	600	600	0	120
All providers	baseline:direct-facts	minimax-m3	exact_world	-33.0%	-36.5% to -29.5%	600	600	0	120
All providers	baseline:direct-facts	minimax-m3	task_success	-33.0%	-36.5% to -29.5%	600	600	0	120
All providers	baseline:direct-facts	minimax-m3	decision_correct	-62.5%	-71.0% to -54.2%	600	600	0	120
All providers	baseline:direct-facts	qwen3.8-27b	fact_f1	-9.9%	-12.3% to -7.6%	600	600	0	120
All providers	baseline:direct-facts	qwen3.8-27b	exact_world	-32.8%	-37.0% to -28.8%	600	600	0	120
All providers	baseline:direct-facts	qwen3.8-27b	task_success	-32.8%	-37.0% to -28.8%	600	600	0	120
All providers	baseline:direct-facts	qwen3.8-27b	decision_correct	-62.8%	-71.0% to -54.7%	600	600	0	120
All providers	baseline:forward-chain	baseline:story-copy	fact_f1	99.8%	99.6% to 100.0%	600	600	0	120
All providers	baseline:forward-chain	baseline:story-copy	exact_world	98.3%	95.8% to 100.0%	600	600	0	120
All providers	baseline:forward-chain	baseline:story-copy	task_success	98.3%	95.8% to 100.0%	600	600	0	120
All providers	baseline:forward-chain	baseline:story-copy	decision_correct	99.2%	97.5% to 100.0%	600	600	0	120
All providers	baseline:forward-chain	claude-fable-5	fact_f1	4.4%	3.5% to 5.4%	600	393	207	120
All providers	baseline:forward-chain	claude-fable-5	exact_world	38.7%	32.9% to 44.3%	600	393	207	120
All providers	baseline:forward-chain	claude-fable-5	task_success	38.7%	32.9% to 44.3%	600	393	207	120
All providers	baseline:forward-chain	claude-fable-5	decision_correct	0.8%	-0.8% to 2.5%	600	393	207	120
All providers	baseline:forward-chain	claude-fable-5.1	fact_f1	1.8%	0.3% to 3.5%	600	14	586	13
All providers	baseline:forward-chain	claude-fable-5.1	exact_world	28.6%	7.7% to 50.0%	600	14	586	13
All providers	baseline:forward-chain	claude-fable-5.1	task_success	28.6%	7.7% to 50.0%	600	14	586	13
All providers	baseline:forward-chain	claude-fable-5.1	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	baseline:forward-chain	claude-haiku-4.5	fact_f1	31.8%	28.9% to 34.6%	600	600	0	120
All providers	baseline:forward-chain	claude-haiku-4.5	exact_world	74.7%	71.7% to 77.2%	600	600	0	120
All providers	baseline:forward-chain	claude-haiku-4.5	task_success	74.7%	71.7% to 77.2%	600	600	0	120
All providers	baseline:forward-chain	claude-haiku-4.5	decision_correct	3.7%	2.2% to 5.2%	600	600	0	120
All providers	baseline:forward-chain	claude-opus-5	fact_f1	18.8%	15.6% to 21.9%	600	424	176	119
All providers	baseline:forward-chain	claude-opus-5	exact_world	45.5%	38.7% to 51.8%	600	424	176	119
All providers	baseline:forward-chain	claude-opus-5	task_success	45.5%	38.7% to 51.8%	600	424	176	119
All providers	baseline:forward-chain	claude-opus-5	decision_correct	7.5%	4.1% to 10.7%	600	424	176	119
All providers	baseline:forward-chain	claude-opus-5.5	fact_f1	6.6%	5.7% to 7.5%	600	591	9	120
All providers	baseline:forward-chain	claude-opus-5.5	exact_world	57.7%	53.2% to 61.9%	600	591	9	120
All providers	baseline:forward-chain	claude-opus-5.5	task_success	57.9%	53.4% to 62.0%	600	591	9	120
All providers	baseline:forward-chain	claude-opus-5.5	decision_correct	3.9%	1.3% to 6.1%	600	591	9	120
All providers	baseline:forward-chain	claude-sonnet-5	fact_f1	9.6%	7.5% to 11.8%	600	445	155	120
All providers	baseline:forward-chain	claude-sonnet-5	exact_world	41.6%	36.4% to 46.9%	600	445	155	120
All providers	baseline:forward-chain	claude-sonnet-5	task_success	41.6%	36.4% to 46.9%	600	445	155	120
All providers	baseline:forward-chain	claude-sonnet-5	decision_correct	2.9%	0.7% to 5.0%	600	445	155	120
All providers	baseline:forward-chain	deepseek-4.1-flash	fact_f1	20.5%	18.1% to 22.8%	600	595	5	120
All providers	baseline:forward-chain	deepseek-4.1-flash	exact_world	49.4%	44.6% to 54.1%	600	595	5	120
All providers	baseline:forward-chain	deepseek-4.1-flash	task_success	49.4%	44.6% to 54.1%	600	595	5	120
All providers	baseline:forward-chain	deepseek-4.1-flash	decision_correct	-0.7%	-2.0% to 0.0%	600	595	5	120
All providers	baseline:forward-chain	deepseek-v4-pro	fact_f1	8.4%	7.1% to 9.7%	600	600	0	120
All providers	baseline:forward-chain	deepseek-v4-pro	exact_world	55.7%	50.5% to 60.0%	600	600	0	120
All providers	baseline:forward-chain	deepseek-v4-pro	task_success	55.7%	50.5% to 60.0%	600	600	0	120
All providers	baseline:forward-chain	deepseek-v4-pro	decision_correct	3.8%	1.5% to 6.2%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.6-flash	fact_f1	20.4%	17.7% to 23.0%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.6-flash	exact_world	54.7%	49.8% to 59.2%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.6-flash	task_success	54.7%	49.8% to 59.2%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.6-flash	decision_correct	0.2%	-0.8% to 1.0%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.7-flash	fact_f1	8.5%	6.9% to 10.3%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.7-flash	exact_world	29.7%	25.5% to 33.8%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.7-flash	task_success	29.7%	25.5% to 33.8%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.7-flash	decision_correct	-0.3%	-1.5% to 0.5%	600	600	0	120
All providers	baseline:forward-chain	gemini-3.8-flash	fact_f1	13.3%	11.2% to 15.4%	600	598	2	120
All providers	baseline:forward-chain	gemini-3.8-flash	exact_world	39.1%	34.2% to 43.7%	600	598	2	120
All providers	baseline:forward-chain	gemini-3.8-flash	task_success	39.1%	34.2% to 43.7%	600	598	2	120
All providers	baseline:forward-chain	gemini-3.8-flash	decision_correct	-0.5%	-2.0% to 0.5%	600	598	2	120
All providers	baseline:forward-chain	glm-4.7-flash	fact_f1	32.8%	29.9% to 35.5%	600	566	34	120
All providers	baseline:forward-chain	glm-4.7-flash	exact_world	78.3%	75.3% to 81.0%	600	566	34	120
All providers	baseline:forward-chain	glm-4.7-flash	task_success	78.3%	75.3% to 81.0%	600	566	34	120
All providers	baseline:forward-chain	glm-4.7-flash	decision_correct	17.3%	14.0% to 20.7%	600	566	34	120
All providers	baseline:forward-chain	glm-5.3	fact_f1	14.7%	11.7% to 17.7%	600	564	36	120
All providers	baseline:forward-chain	glm-5.3	exact_world	41.8%	36.5% to 46.7%	600	564	36	120
All providers	baseline:forward-chain	glm-5.3	task_success	42.0%	36.8% to 46.9%	600	564	36	120
All providers	baseline:forward-chain	glm-5.3	decision_correct	3.0%	0.7% to 5.0%	600	564	36	120
All providers	baseline:forward-chain	glm-5.3-flash	fact_f1	32.7%	29.4% to 36.0%	600	596	4	120
All providers	baseline:forward-chain	glm-5.3-flash	exact_world	72.1%	68.3% to 75.7%	600	596	4	120
All providers	baseline:forward-chain	glm-5.3-flash	task_success	72.3%	68.4% to 75.9%	600	596	4	120
All providers	baseline:forward-chain	glm-5.3-flash	decision_correct	0.8%	-1.4% to 2.5%	600	596	4	120
All providers	baseline:forward-chain	gpt-5.6-luna	fact_f1	18.5%	16.4% to 20.5%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-luna	exact_world	55.7%	51.2% to 59.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-luna	task_success	56.7%	52.2% to 60.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-luna	decision_correct	2.0%	-0.0% to 3.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-sol	fact_f1	8.8%	7.0% to 10.6%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-sol	exact_world	29.8%	24.7% to 35.2%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-sol	task_success	29.8%	24.7% to 35.2%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-sol	decision_correct	-0.8%	-2.5% to 0.0%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-terra	fact_f1	18.1%	16.0% to 20.2%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-terra	exact_world	47.7%	43.0% to 51.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-terra	task_success	47.7%	43.0% to 51.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-5.6-terra	decision_correct	-0.7%	-2.0% to 0.0%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-astra	fact_f1	1.1%	0.5% to 1.6%	600	550	50	115
All providers	baseline:forward-chain	gpt-6-astra	exact_world	10.7%	6.2% to 15.5%	600	550	50	115
All providers	baseline:forward-chain	gpt-6-astra	task_success	10.7%	6.2% to 15.5%	600	550	50	115
All providers	baseline:forward-chain	gpt-6-astra	decision_correct	-0.7%	-2.2% to 0.0%	600	550	50	115
All providers	baseline:forward-chain	gpt-6-luna	fact_f1	18.4%	16.2% to 20.6%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-luna	exact_world	55.8%	51.7% to 59.7%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-luna	task_success	56.0%	51.7% to 59.8%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-luna	decision_correct	0.8%	-1.3% to 2.5%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-sol	fact_f1	3.2%	2.4% to 4.0%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-sol	exact_world	24.0%	19.5% to 28.5%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-sol	task_success	24.2%	19.7% to 28.7%	600	600	0	120
All providers	baseline:forward-chain	gpt-6-sol	decision_correct	0.7%	-1.2% to 2.0%	600	600	0	120
All providers	baseline:forward-chain	grok-4.6	fact_f1	10.4%	9.1% to 11.6%	600	600	0	120
All providers	baseline:forward-chain	grok-4.6	exact_world	61.3%	57.0% to 65.3%	600	600	0	120
All providers	baseline:forward-chain	grok-4.6	task_success	61.3%	57.0% to 65.3%	600	600	0	120
All providers	baseline:forward-chain	grok-4.6	decision_correct	2.5%	0.7% to 4.7%	600	600	0	120
All providers	baseline:forward-chain	kimi-k2.6	fact_f1	9.3%	8.2% to 10.5%	600	599	1	120
All providers	baseline:forward-chain	kimi-k2.6	exact_world	61.8%	57.8% to 65.6%	600	599	1	120
All providers	baseline:forward-chain	kimi-k2.6	task_success	61.8%	57.8% to 65.6%	600	599	1	120
All providers	baseline:forward-chain	kimi-k2.6	decision_correct	1.3%	-1.0% to 3.3%	600	599	1	120
All providers	baseline:forward-chain	kimi-k3	fact_f1	14.8%	12.0% to 17.7%	600	443	157	96
All providers	baseline:forward-chain	kimi-k3	exact_world	55.5%	50.1% to 60.5%	600	443	157	96
All providers	baseline:forward-chain	kimi-k3	task_success	55.5%	50.1% to 60.5%	600	443	157	96
All providers	baseline:forward-chain	kimi-k3	decision_correct	-0.9%	-2.8% to 0.0%	600	443	157	96
All providers	baseline:forward-chain	mimo-v2.6-flash	fact_f1	20.5%	18.2% to 22.7%	600	594	6	120
All providers	baseline:forward-chain	mimo-v2.6-flash	exact_world	57.4%	53.0% to 61.3%	600	594	6	120
All providers	baseline:forward-chain	mimo-v2.6-flash	task_success	59.1%	54.6% to 63.1%	600	594	6	120
All providers	baseline:forward-chain	mimo-v2.6-flash	decision_correct	9.3%	6.2% to 12.3%	600	594	6	120
All providers	baseline:forward-chain	mimo-v2.6-pro	fact_f1	23.2%	20.7% to 25.8%	600	600	0	120
All providers	baseline:forward-chain	mimo-v2.6-pro	exact_world	59.2%	54.8% to 63.3%	600	600	0	120
All providers	baseline:forward-chain	mimo-v2.6-pro	task_success	60.3%	56.0% to 64.8%	600	600	0	120
All providers	baseline:forward-chain	mimo-v2.6-pro	decision_correct	10.7%	7.2% to 14.0%	600	600	0	120
All providers	baseline:forward-chain	minimax-m3	fact_f1	31.4%	28.2% to 34.6%	600	600	0	120
All providers	baseline:forward-chain	minimax-m3	exact_world	64.5%	60.2% to 68.3%	600	600	0	120
All providers	baseline:forward-chain	minimax-m3	task_success	64.5%	60.2% to 68.3%	600	600	0	120
All providers	baseline:forward-chain	minimax-m3	decision_correct	2.5%	0.7% to 4.2%	600	600	0	120
All providers	baseline:forward-chain	qwen3.8-27b	fact_f1	16.2%	14.1% to 18.5%	600	600	0	120
All providers	baseline:forward-chain	qwen3.8-27b	exact_world	64.7%	60.0% to 68.8%	600	600	0	120
All providers	baseline:forward-chain	qwen3.8-27b	task_success	64.7%	60.0% to 68.8%	600	600	0	120
All providers	baseline:forward-chain	qwen3.8-27b	decision_correct	2.2%	0.7% to 3.8%	600	600	0	120
All providers	baseline:story-copy	claude-fable-5	fact_f1	-95.5%	-96.4% to -94.5%	600	393	207	120
All providers	baseline:story-copy	claude-fable-5	exact_world	-60.3%	-66.0% to -54.8%	600	393	207	120
All providers	baseline:story-copy	claude-fable-5	task_success	-60.3%	-66.0% to -54.8%	600	393	207	120
All providers	baseline:story-copy	claude-fable-5	decision_correct	-98.7%	-99.8% to -97.3%	600	393	207	120
All providers	baseline:story-copy	claude-fable-5.1	fact_f1	-98.2%	-99.7% to -96.5%	600	14	586	13
All providers	baseline:story-copy	claude-fable-5.1	exact_world	-71.4%	-92.3% to -50.0%	600	14	586	13
All providers	baseline:story-copy	claude-fable-5.1	task_success	-71.4%	-92.3% to -50.0%	600	14	586	13
All providers	baseline:story-copy	claude-fable-5.1	decision_correct	-100.0%	-100.0% to -100.0%	600	14	586	13
All providers	baseline:story-copy	claude-haiku-4.5	fact_f1	-68.0%	-70.9% to -65.2%	600	600	0	120
All providers	baseline:story-copy	claude-haiku-4.5	exact_world	-23.7%	-25.7% to -21.8%	600	600	0	120
All providers	baseline:story-copy	claude-haiku-4.5	task_success	-23.7%	-25.7% to -21.8%	600	600	0	120
All providers	baseline:story-copy	claude-haiku-4.5	decision_correct	-95.5%	-97.3% to -93.5%	600	600	0	120
All providers	baseline:story-copy	claude-opus-5	fact_f1	-81.1%	-84.3% to -77.9%	600	424	176	119
All providers	baseline:story-copy	claude-opus-5	exact_world	-52.6%	-58.3% to -47.2%	600	424	176	119
All providers	baseline:story-copy	claude-opus-5	task_success	-52.6%	-58.3% to -47.2%	600	424	176	119
All providers	baseline:story-copy	claude-opus-5	decision_correct	-91.5%	-94.1% to -88.6%	600	424	176	119
All providers	baseline:story-copy	claude-opus-5.5	fact_f1	-93.3%	-94.1% to -92.4%	600	591	9	120
All providers	baseline:story-copy	claude-opus-5.5	exact_world	-40.6%	-44.3% to -37.2%	600	591	9	120
All providers	baseline:story-copy	claude-opus-5.5	task_success	-40.4%	-44.2% to -37.0%	600	591	9	120
All providers	baseline:story-copy	claude-opus-5.5	decision_correct	-95.3%	-97.1% to -93.1%	600	591	9	120
All providers	baseline:story-copy	claude-sonnet-5	fact_f1	-90.2%	-92.4% to -88.1%	600	445	155	120
All providers	baseline:story-copy	claude-sonnet-5	exact_world	-56.4%	-60.9% to -51.3%	600	445	155	120
All providers	baseline:story-copy	claude-sonnet-5	task_success	-56.4%	-60.9% to -51.3%	600	445	155	120
All providers	baseline:story-copy	claude-sonnet-5	decision_correct	-96.0%	-97.7% to -94.1%	600	445	155	120
All providers	baseline:story-copy	deepseek-4.1-flash	fact_f1	-79.4%	-81.7% to -77.1%	600	595	5	120
All providers	baseline:story-copy	deepseek-4.1-flash	exact_world	-49.1%	-53.1% to -44.9%	600	595	5	120
All providers	baseline:story-copy	deepseek-4.1-flash	task_success	-49.1%	-53.1% to -44.9%	600	595	5	120
All providers	baseline:story-copy	deepseek-4.1-flash	decision_correct	-100.0%	-100.0% to -100.0%	600	595	5	120
All providers	baseline:story-copy	deepseek-v4-pro	fact_f1	-91.5%	-92.7% to -90.2%	600	600	0	120
All providers	baseline:story-copy	deepseek-v4-pro	exact_world	-42.7%	-46.8% to -38.8%	600	600	0	120
All providers	baseline:story-copy	deepseek-v4-pro	task_success	-42.7%	-46.8% to -38.8%	600	600	0	120
All providers	baseline:story-copy	deepseek-v4-pro	decision_correct	-95.3%	-97.2% to -93.3%	600	600	0	120
All providers	baseline:story-copy	gemini-3.6-flash	fact_f1	-79.5%	-82.1% to -76.8%	600	600	0	120
All providers	baseline:story-copy	gemini-3.6-flash	exact_world	-43.7%	-47.8% to -39.3%	600	600	0	120
All providers	baseline:story-copy	gemini-3.6-flash	task_success	-43.7%	-47.8% to -39.3%	600	600	0	120
All providers	baseline:story-copy	gemini-3.6-flash	decision_correct	-99.0%	-99.8% to -97.8%	600	600	0	120
All providers	baseline:story-copy	gemini-3.7-flash	fact_f1	-91.3%	-93.0% to -89.5%	600	600	0	120
All providers	baseline:story-copy	gemini-3.7-flash	exact_world	-68.7%	-72.8% to -64.8%	600	600	0	120
All providers	baseline:story-copy	gemini-3.7-flash	task_success	-68.7%	-72.8% to -64.8%	600	600	0	120
All providers	baseline:story-copy	gemini-3.7-flash	decision_correct	-99.5%	-100.0% to -98.7%	600	600	0	120
All providers	baseline:story-copy	gemini-3.8-flash	fact_f1	-86.5%	-88.7% to -84.4%	600	598	2	120
All providers	baseline:story-copy	gemini-3.8-flash	exact_world	-59.2%	-63.6% to -55.0%	600	598	2	120
All providers	baseline:story-copy	gemini-3.8-flash	task_success	-59.2%	-63.6% to -55.0%	600	598	2	120
All providers	baseline:story-copy	gemini-3.8-flash	decision_correct	-99.7%	-100.0% to -99.2%	600	598	2	120
All providers	baseline:story-copy	glm-4.7-flash	fact_f1	-67.1%	-69.9% to -64.4%	600	566	34	120
All providers	baseline:story-copy	glm-4.7-flash	exact_world	-20.7%	-23.0% to -18.5%	600	566	34	120
All providers	baseline:story-copy	glm-4.7-flash	task_success	-20.7%	-23.0% to -18.5%	600	566	34	120
All providers	baseline:story-copy	glm-4.7-flash	decision_correct	-82.5%	-85.8% to -79.1%	600	566	34	120
All providers	baseline:story-copy	glm-5.3	fact_f1	-85.2%	-88.1% to -82.2%	600	564	36	120
All providers	baseline:story-copy	glm-5.3	exact_world	-56.7%	-61.5% to -52.2%	600	564	36	120
All providers	baseline:story-copy	glm-5.3	task_success	-56.6%	-61.4% to -52.1%	600	564	36	120
All providers	baseline:story-copy	glm-5.3	decision_correct	-96.3%	-97.7% to -94.6%	600	564	36	120
All providers	baseline:story-copy	glm-5.3-flash	fact_f1	-67.1%	-70.5% to -63.9%	600	596	4	120
All providers	baseline:story-copy	glm-5.3-flash	exact_world	-26.2%	-29.4% to -23.2%	600	596	4	120
All providers	baseline:story-copy	glm-5.3-flash	task_success	-26.0%	-29.3% to -23.0%	600	596	4	120
All providers	baseline:story-copy	glm-5.3-flash	decision_correct	-98.3%	-99.2% to -97.3%	600	596	4	120
All providers	baseline:story-copy	gpt-5.6-luna	fact_f1	-81.4%	-83.4% to -79.4%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-luna	exact_world	-42.7%	-46.0% to -39.3%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-luna	task_success	-41.7%	-45.0% to -38.3%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-luna	decision_correct	-97.2%	-98.5% to -95.7%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-sol	fact_f1	-91.0%	-92.8% to -89.3%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-sol	exact_world	-68.5%	-72.8% to -63.8%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-sol	task_success	-68.5%	-72.8% to -63.8%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-sol	decision_correct	-100.0%	-100.0% to -100.0%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-terra	fact_f1	-81.8%	-83.8% to -79.7%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-terra	exact_world	-50.7%	-54.3% to -47.0%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-terra	task_success	-50.7%	-54.3% to -47.0%	600	600	0	120
All providers	baseline:story-copy	gpt-5.6-terra	decision_correct	-99.8%	-100.0% to -99.5%	600	600	0	120
All providers	baseline:story-copy	gpt-6-astra	fact_f1	-98.8%	-99.2% to -98.3%	600	550	50	115
All providers	baseline:story-copy	gpt-6-astra	exact_world	-87.6%	-91.3% to -83.5%	600	550	50	115
All providers	baseline:story-copy	gpt-6-astra	task_success	-87.6%	-91.3% to -83.5%	600	550	50	115
All providers	baseline:story-copy	gpt-6-astra	decision_correct	-100.0%	-100.0% to -100.0%	600	550	50	115
All providers	baseline:story-copy	gpt-6-luna	fact_f1	-81.5%	-83.7% to -79.2%	600	600	0	120
All providers	baseline:story-copy	gpt-6-luna	exact_world	-42.5%	-46.3% to -39.0%	600	600	0	120
All providers	baseline:story-copy	gpt-6-luna	task_success	-42.3%	-46.0% to -38.8%	600	600	0	120
All providers	baseline:story-copy	gpt-6-luna	decision_correct	-98.3%	-99.3% to -97.3%	600	600	0	120
All providers	baseline:story-copy	gpt-6-sol	fact_f1	-96.6%	-97.4% to -95.8%	600	600	0	120
All providers	baseline:story-copy	gpt-6-sol	exact_world	-74.3%	-78.5% to -70.2%	600	600	0	120
All providers	baseline:story-copy	gpt-6-sol	task_success	-74.2%	-78.3% to -70.0%	600	600	0	120
All providers	baseline:story-copy	gpt-6-sol	decision_correct	-98.5%	-99.3% to -97.5%	600	600	0	120
All providers	baseline:story-copy	grok-4.6	fact_f1	-89.5%	-90.7% to -88.3%	600	600	0	120
All providers	baseline:story-copy	grok-4.6	exact_world	-37.0%	-40.8% to -33.5%	600	600	0	120
All providers	baseline:story-copy	grok-4.6	task_success	-37.0%	-40.8% to -33.5%	600	600	0	120
All providers	baseline:story-copy	grok-4.6	decision_correct	-96.7%	-98.7% to -94.5%	600	600	0	120
All providers	baseline:story-copy	kimi-k2.6	fact_f1	-90.6%	-91.7% to -89.3%	600	599	1	120
All providers	baseline:story-copy	kimi-k2.6	exact_world	-36.6%	-40.1% to -33.1%	600	599	1	120
All providers	baseline:story-copy	kimi-k2.6	task_success	-36.6%	-40.1% to -33.1%	600	599	1	120
All providers	baseline:story-copy	kimi-k2.6	decision_correct	-97.8%	-99.0% to -96.5%	600	599	1	120
All providers	baseline:story-copy	kimi-k3	fact_f1	-85.0%	-87.8% to -82.1%	600	443	157	96
All providers	baseline:story-copy	kimi-k3	exact_world	-42.2%	-47.0% to -37.6%	600	443	157	96
All providers	baseline:story-copy	kimi-k3	task_success	-42.2%	-47.0% to -37.6%	600	443	157	96
All providers	baseline:story-copy	kimi-k3	decision_correct	-99.8%	-100.0% to -99.3%	600	443	157	96
All providers	baseline:story-copy	mimo-v2.6-flash	fact_f1	-79.3%	-81.7% to -77.1%	600	594	6	120
All providers	baseline:story-copy	mimo-v2.6-flash	exact_world	-40.9%	-44.4% to -37.7%	600	594	6	120
All providers	baseline:story-copy	mimo-v2.6-flash	task_success	-39.2%	-42.8% to -36.0%	600	594	6	120
All providers	baseline:story-copy	mimo-v2.6-flash	decision_correct	-89.9%	-92.5% to -87.1%	600	594	6	120
All providers	baseline:story-copy	mimo-v2.6-pro	fact_f1	-76.6%	-79.1% to -74.0%	600	600	0	120
All providers	baseline:story-copy	mimo-v2.6-pro	exact_world	-39.2%	-42.7% to -35.7%	600	600	0	120
All providers	baseline:story-copy	mimo-v2.6-pro	task_success	-38.0%	-41.5% to -34.3%	600	600	0	120
All providers	baseline:story-copy	mimo-v2.6-pro	decision_correct	-88.5%	-91.2% to -85.7%	600	600	0	120
All providers	baseline:story-copy	minimax-m3	fact_f1	-68.5%	-71.7% to -65.3%	600	600	0	120
All providers	baseline:story-copy	minimax-m3	exact_world	-33.8%	-37.2% to -30.7%	600	600	0	120
All providers	baseline:story-copy	minimax-m3	task_success	-33.8%	-37.2% to -30.7%	600	600	0	120
All providers	baseline:story-copy	minimax-m3	decision_correct	-96.7%	-98.2% to -95.0%	600	600	0	120
All providers	baseline:story-copy	qwen3.8-27b	fact_f1	-83.6%	-85.7% to -81.3%	600	600	0	120
All providers	baseline:story-copy	qwen3.8-27b	exact_world	-33.7%	-37.5% to -30.2%	600	600	0	120
All providers	baseline:story-copy	qwen3.8-27b	task_success	-33.7%	-37.5% to -30.2%	600	600	0	120
All providers	baseline:story-copy	qwen3.8-27b	decision_correct	-97.0%	-98.5% to -95.2%	600	600	0	120
All providers	claude-fable-5	claude-fable-5.1	fact_f1	-1.3%	-3.0% to 0.0%	600	9	591	9
All providers	claude-fable-5	claude-fable-5.1	exact_world	-11.1%	-33.3% to 0.0%	600	9	591	9
All providers	claude-fable-5	claude-fable-5.1	task_success	-11.1%	-33.3% to 0.0%	600	9	591	9
All providers	claude-fable-5	claude-fable-5.1	decision_correct	0.0%	0.0% to 0.0%	600	9	591	9
All providers	claude-fable-5	claude-haiku-4.5	fact_f1	25.5%	21.9% to 29.1%	600	393	207	120
All providers	claude-fable-5	claude-haiku-4.5	exact_world	33.8%	27.9% to 39.6%	600	393	207	120
All providers	claude-fable-5	claude-haiku-4.5	task_success	33.8%	27.9% to 39.6%	600	393	207	120
All providers	claude-fable-5	claude-haiku-4.5	decision_correct	3.1%	0.5% to 5.7%	600	393	207	120
All providers	claude-fable-5	claude-opus-5	fact_f1	12.0%	7.7% to 16.4%	600	268	332	112
All providers	claude-fable-5	claude-opus-5	exact_world	-4.1%	-14.1% to 5.5%	600	268	332	112
All providers	claude-fable-5	claude-opus-5	task_success	-4.1%	-14.1% to 5.5%	600	268	332	112
All providers	claude-fable-5	claude-opus-5	decision_correct	6.3%	2.9% to 9.9%	600	268	332	112
All providers	claude-fable-5	claude-opus-5.5	fact_f1	1.8%	0.5% to 3.0%	600	388	212	120
All providers	claude-fable-5	claude-opus-5.5	exact_world	17.8%	11.3% to 24.3%	600	388	212	120
All providers	claude-fable-5	claude-opus-5.5	task_success	17.8%	11.3% to 24.3%	600	388	212	120
All providers	claude-fable-5	claude-opus-5.5	decision_correct	4.1%	1.3% to 7.1%	600	388	212	120
All providers	claude-fable-5	claude-sonnet-5	fact_f1	5.4%	2.7% to 8.1%	600	292	308	117
All providers	claude-fable-5	claude-sonnet-5	exact_world	9.6%	2.4% to 16.8%	600	292	308	117
All providers	claude-fable-5	claude-sonnet-5	task_success	9.6%	2.4% to 16.8%	600	292	308	117
All providers	claude-fable-5	claude-sonnet-5	decision_correct	3.8%	1.4% to 6.0%	600	292	308	117
All providers	claude-fable-5	deepseek-4.1-flash	fact_f1	12.0%	9.3% to 14.7%	600	390	210	120
All providers	claude-fable-5	deepseek-4.1-flash	exact_world	5.6%	-1.1% to 12.1%	600	390	210	120
All providers	claude-fable-5	deepseek-4.1-flash	task_success	5.6%	-1.1% to 12.1%	600	390	210	120
All providers	claude-fable-5	deepseek-4.1-flash	decision_correct	-1.3%	-2.7% to -0.2%	600	390	210	120
All providers	claude-fable-5	deepseek-v4-pro	fact_f1	2.8%	1.1% to 4.7%	600	393	207	120
All providers	claude-fable-5	deepseek-v4-pro	exact_world	14.0%	7.2% to 20.6%	600	393	207	120
All providers	claude-fable-5	deepseek-v4-pro	task_success	14.0%	7.2% to 20.6%	600	393	207	120
All providers	claude-fable-5	deepseek-v4-pro	decision_correct	3.6%	0.8% to 6.5%	600	393	207	120
All providers	claude-fable-5	gemini-3.6-flash	fact_f1	14.0%	10.8% to 17.1%	600	393	207	120
All providers	claude-fable-5	gemini-3.6-flash	exact_world	14.0%	7.2% to 20.6%	600	393	207	120
All providers	claude-fable-5	gemini-3.6-flash	task_success	14.0%	7.2% to 20.6%	600	393	207	120
All providers	claude-fable-5	gemini-3.6-flash	decision_correct	-0.8%	-2.2% to 0.3%	600	393	207	120
All providers	claude-fable-5	gemini-3.7-flash	fact_f1	3.4%	1.5% to 5.4%	600	393	207	120
All providers	claude-fable-5	gemini-3.7-flash	exact_world	-9.7%	-16.5% to -3.1%	600	393	207	120
All providers	claude-fable-5	gemini-3.7-flash	task_success	-9.7%	-16.5% to -3.1%	600	393	207	120
All providers	claude-fable-5	gemini-3.7-flash	decision_correct	-1.0%	-2.5% to 0.3%	600	393	207	120
All providers	claude-fable-5	gemini-3.8-flash	fact_f1	6.9%	4.4% to 9.2%	600	391	209	120
All providers	claude-fable-5	gemini-3.8-flash	exact_world	-2.8%	-9.5% to 4.0%	600	391	209	120
All providers	claude-fable-5	gemini-3.8-flash	task_success	-2.8%	-9.5% to 4.0%	600	391	209	120
All providers	claude-fable-5	gemini-3.8-flash	decision_correct	-0.8%	-2.3% to 0.5%	600	391	209	120
All providers	claude-fable-5	glm-4.7-flash	fact_f1	26.6%	23.5% to 29.9%	600	369	231	119
All providers	claude-fable-5	glm-4.7-flash	exact_world	37.4%	31.9% to 43.4%	600	369	231	119
All providers	claude-fable-5	glm-4.7-flash	task_success	37.4%	31.9% to 43.4%	600	369	231	119
All providers	claude-fable-5	glm-4.7-flash	decision_correct	16.3%	12.0% to 20.6%	600	369	231	119
All providers	claude-fable-5	glm-5.3	fact_f1	10.2%	6.8% to 13.8%	600	368	232	119
All providers	claude-fable-5	glm-5.3	exact_world	3.8%	-3.5% to 11.1%	600	368	232	119
All providers	claude-fable-5	glm-5.3	task_success	4.1%	-3.1% to 11.4%	600	368	232	119
All providers	claude-fable-5	glm-5.3	decision_correct	2.7%	0.5% to 4.9%	600	368	232	119
All providers	claude-fable-5	glm-5.3-flash	fact_f1	25.7%	21.4% to 29.5%	600	390	210	120
All providers	claude-fable-5	glm-5.3-flash	exact_world	31.5%	25.1% to 38.0%	600	390	210	120
All providers	claude-fable-5	glm-5.3-flash	task_success	31.8%	25.4% to 38.2%	600	390	210	120
All providers	claude-fable-5	glm-5.3-flash	decision_correct	-0.5%	-2.1% to 1.0%	600	390	210	120
All providers	claude-fable-5	gpt-5.6-luna	fact_f1	11.2%	8.8% to 13.6%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-luna	exact_world	14.5%	8.0% to 21.4%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-luna	task_success	15.8%	9.3% to 22.8%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-luna	decision_correct	1.8%	-0.5% to 4.1%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-sol	fact_f1	3.7%	1.5% to 5.8%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-sol	exact_world	-8.4%	-16.2% to -0.5%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-sol	task_success	-8.4%	-16.2% to -0.5%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-sol	decision_correct	-1.3%	-2.7% to -0.2%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-terra	fact_f1	12.2%	9.4% to 14.8%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-terra	exact_world	8.9%	1.9% to 15.6%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-terra	task_success	8.9%	1.9% to 15.6%	600	393	207	120
All providers	claude-fable-5	gpt-5.6-terra	decision_correct	-1.3%	-2.7% to -0.2%	600	393	207	120
All providers	claude-fable-5	gpt-6-astra	fact_f1	-3.6%	-4.7% to -2.5%	600	362	238	115
All providers	claude-fable-5	gpt-6-astra	exact_world	-28.2%	-34.5% to -21.4%	600	362	238	115
All providers	claude-fable-5	gpt-6-astra	task_success	-28.2%	-34.5% to -21.4%	600	362	238	115
All providers	claude-fable-5	gpt-6-astra	decision_correct	-1.4%	-2.9% to -0.3%	600	362	238	115
All providers	claude-fable-5	gpt-6-luna	fact_f1	12.0%	9.3% to 14.7%	600	393	207	120
All providers	claude-fable-5	gpt-6-luna	exact_world	15.5%	9.4% to 21.7%	600	393	207	120
All providers	claude-fable-5	gpt-6-luna	task_success	15.8%	9.6% to 22.0%	600	393	207	120
All providers	claude-fable-5	gpt-6-luna	decision_correct	0.5%	-1.3% to 2.3%	600	393	207	120
All providers	claude-fable-5	gpt-6-sol	fact_f1	-1.8%	-2.9% to -0.7%	600	393	207	120
All providers	claude-fable-5	gpt-6-sol	exact_world	-14.8%	-21.0% to -8.4%	600	393	207	120
All providers	claude-fable-5	gpt-6-sol	task_success	-14.5%	-20.8% to -8.1%	600	393	207	120
All providers	claude-fable-5	gpt-6-sol	decision_correct	0.0%	-1.7% to 1.5%	600	393	207	120
All providers	claude-fable-5	grok-4.6	fact_f1	5.1%	3.6% to 6.6%	600	393	207	120
All providers	claude-fable-5	grok-4.6	exact_world	20.6%	14.8% to 26.4%	600	393	207	120
All providers	claude-fable-5	grok-4.6	task_success	20.6%	14.8% to 26.4%	600	393	207	120
All providers	claude-fable-5	grok-4.6	decision_correct	2.8%	0.2% to 5.6%	600	393	207	120
All providers	claude-fable-5	kimi-k2.6	fact_f1	3.7%	2.4% to 5.1%	600	393	207	120
All providers	claude-fable-5	kimi-k2.6	exact_world	21.6%	16.1% to 26.9%	600	393	207	120
All providers	claude-fable-5	kimi-k2.6	task_success	21.6%	16.1% to 26.9%	600	393	207	120
All providers	claude-fable-5	kimi-k2.6	decision_correct	1.5%	-0.5% to 3.7%	600	393	207	120
All providers	claude-fable-5	kimi-k3	fact_f1	10.1%	6.6% to 13.5%	600	293	307	94
All providers	claude-fable-5	kimi-k3	exact_world	16.4%	10.3% to 22.6%	600	293	307	94
All providers	claude-fable-5	kimi-k3	task_success	16.4%	10.3% to 22.6%	600	293	307	94
All providers	claude-fable-5	kimi-k3	decision_correct	-1.0%	-2.8% to 0.4%	600	293	307	94
All providers	claude-fable-5	mimo-v2.6-flash	fact_f1	14.2%	11.2% to 16.9%	600	387	213	120
All providers	claude-fable-5	mimo-v2.6-flash	exact_world	15.8%	10.2% to 21.4%	600	387	213	120
All providers	claude-fable-5	mimo-v2.6-flash	task_success	17.3%	11.6% to 23.1%	600	387	213	120
All providers	claude-fable-5	mimo-v2.6-flash	decision_correct	9.0%	5.8% to 12.7%	600	387	213	120
All providers	claude-fable-5	mimo-v2.6-pro	fact_f1	16.7%	13.5% to 19.9%	600	393	207	120
All providers	claude-fable-5	mimo-v2.6-pro	exact_world	15.5%	9.2% to 21.7%	600	393	207	120
All providers	claude-fable-5	mimo-v2.6-pro	task_success	17.0%	10.7% to 23.4%	600	393	207	120
All providers	claude-fable-5	mimo-v2.6-pro	decision_correct	10.7%	7.1% to 14.4%	600	393	207	120
All providers	claude-fable-5	minimax-m3	fact_f1	24.6%	20.7% to 28.4%	600	393	207	120
All providers	claude-fable-5	minimax-m3	exact_world	22.6%	16.4% to 28.8%	600	393	207	120
All providers	claude-fable-5	minimax-m3	task_success	22.6%	16.4% to 28.8%	600	393	207	120
All providers	claude-fable-5	minimax-m3	decision_correct	2.8%	0.3% to 5.4%	600	393	207	120
All providers	claude-fable-5	qwen3.8-27b	fact_f1	10.1%	7.6% to 12.7%	600	393	207	120
All providers	claude-fable-5	qwen3.8-27b	exact_world	25.2%	18.3% to 32.0%	600	393	207	120
All providers	claude-fable-5	qwen3.8-27b	task_success	25.2%	18.3% to 32.0%	600	393	207	120
All providers	claude-fable-5	qwen3.8-27b	decision_correct	2.3%	0.0% to 4.8%	600	393	207	120
All providers	claude-fable-5.1	claude-haiku-4.5	fact_f1	39.4%	24.0% to 53.9%	600	14	586	13
All providers	claude-fable-5.1	claude-haiku-4.5	exact_world	50.0%	26.7% to 73.3%	600	14	586	13
All providers	claude-fable-5.1	claude-haiku-4.5	task_success	50.0%	26.7% to 73.3%	600	14	586	13
All providers	claude-fable-5.1	claude-haiku-4.5	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	claude-opus-5	fact_f1	38.7%	10.3% to 65.2%	600	9	591	8
All providers	claude-fable-5.1	claude-opus-5	exact_world	22.2%	0.0% to 50.0%	600	9	591	8
All providers	claude-fable-5.1	claude-opus-5	task_success	22.2%	0.0% to 50.0%	600	9	591	8
All providers	claude-fable-5.1	claude-opus-5	decision_correct	33.3%	11.1% to 62.5%	600	9	591	8
All providers	claude-fable-5.1	claude-opus-5.5	fact_f1	4.7%	0.3% to 12.9%	600	14	586	13
All providers	claude-fable-5.1	claude-opus-5.5	exact_world	14.3%	0.0% to 35.7%	600	14	586	13
All providers	claude-fable-5.1	claude-opus-5.5	task_success	14.3%	0.0% to 35.7%	600	14	586	13
All providers	claude-fable-5.1	claude-opus-5.5	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	claude-sonnet-5	fact_f1	19.2%	-0.7% to 39.5%	600	8	592	8
All providers	claude-fable-5.1	claude-sonnet-5	exact_world	12.5%	-25.0% to 50.0%	600	8	592	8
All providers	claude-fable-5.1	claude-sonnet-5	task_success	12.5%	-25.0% to 50.0%	600	8	592	8
All providers	claude-fable-5.1	claude-sonnet-5	decision_correct	0.0%	0.0% to 0.0%	600	8	592	8
All providers	claude-fable-5.1	deepseek-4.1-flash	fact_f1	46.1%	27.9% to 62.1%	600	14	586	13
All providers	claude-fable-5.1	deepseek-4.1-flash	exact_world	42.9%	18.8% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	deepseek-4.1-flash	task_success	42.9%	18.8% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	deepseek-4.1-flash	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	deepseek-v4-pro	fact_f1	18.2%	7.1% to 29.2%	600	14	586	13
All providers	claude-fable-5.1	deepseek-v4-pro	exact_world	50.0%	26.7% to 73.3%	600	14	586	13
All providers	claude-fable-5.1	deepseek-v4-pro	task_success	50.0%	26.7% to 73.3%	600	14	586	13
All providers	claude-fable-5.1	deepseek-v4-pro	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.6-flash	fact_f1	34.8%	18.9% to 49.9%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.6-flash	exact_world	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.6-flash	task_success	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.6-flash	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.7-flash	fact_f1	20.7%	7.7% to 36.0%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.7-flash	exact_world	28.6%	6.7% to 53.8%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.7-flash	task_success	28.6%	6.7% to 53.8%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.7-flash	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.8-flash	fact_f1	36.0%	20.6% to 49.8%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.8-flash	exact_world	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.8-flash	task_success	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gemini-3.8-flash	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	glm-4.7-flash	fact_f1	31.1%	14.5% to 50.2%	600	13	587	12
All providers	claude-fable-5.1	glm-4.7-flash	exact_world	53.8%	25.0% to 76.9%	600	13	587	12
All providers	claude-fable-5.1	glm-4.7-flash	task_success	53.8%	25.0% to 76.9%	600	13	587	12
All providers	claude-fable-5.1	glm-4.7-flash	decision_correct	15.4%	0.0% to 38.5%	600	13	587	12
All providers	claude-fable-5.1	glm-5.3	fact_f1	18.5%	4.3% to 33.8%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3	exact_world	35.7%	7.1% to 64.3%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3	task_success	35.7%	7.1% to 64.3%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3	decision_correct	14.3%	0.0% to 33.3%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3-flash	fact_f1	33.5%	14.9% to 53.2%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3-flash	exact_world	57.1%	33.3% to 78.6%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3-flash	task_success	57.1%	33.3% to 78.6%	600	14	586	13
All providers	claude-fable-5.1	glm-5.3-flash	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-luna	fact_f1	23.7%	5.8% to 44.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-luna	exact_world	28.6%	7.7% to 50.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-luna	task_success	28.6%	7.7% to 50.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-luna	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-sol	fact_f1	14.3%	-0.3% to 29.3%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-sol	exact_world	7.1%	-14.3% to 35.7%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-sol	task_success	7.1%	-14.3% to 35.7%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-sol	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-terra	fact_f1	39.8%	18.5% to 61.6%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-terra	exact_world	35.7%	5.9% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-terra	task_success	35.7%	5.9% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	gpt-5.6-terra	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-astra	fact_f1	-0.9%	-2.9% to 0.0%	600	9	591	8
All providers	claude-fable-5.1	gpt-6-astra	exact_world	-11.1%	-37.5% to 0.0%	600	9	591	8
All providers	claude-fable-5.1	gpt-6-astra	task_success	-11.1%	-37.5% to 0.0%	600	9	591	8
All providers	claude-fable-5.1	gpt-6-astra	decision_correct	0.0%	0.0% to 0.0%	600	9	591	8
All providers	claude-fable-5.1	gpt-6-luna	fact_f1	29.8%	10.1% to 51.9%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-luna	exact_world	21.4%	-13.3% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-luna	task_success	21.4%	-13.3% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-luna	decision_correct	7.1%	0.0% to 23.1%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-sol	fact_f1	0.5%	-1.8% to 3.8%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-sol	exact_world	-7.1%	-35.3% to 26.7%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-sol	task_success	-7.1%	-35.3% to 26.7%	600	14	586	13
All providers	claude-fable-5.1	gpt-6-sol	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	grok-4.6	fact_f1	11.3%	4.1% to 20.5%	600	14	586	13
All providers	claude-fable-5.1	grok-4.6	exact_world	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	grok-4.6	task_success	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	grok-4.6	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	kimi-k2.6	fact_f1	19.1%	7.7% to 30.8%	600	14	586	13
All providers	claude-fable-5.1	kimi-k2.6	exact_world	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	kimi-k2.6	task_success	35.7%	12.5% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	kimi-k2.6	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	kimi-k3	fact_f1	40.3%	3.3% to 64.9%	600	5	595	4
All providers	claude-fable-5.1	kimi-k3	exact_world	40.0%	0.0% to 75.0%	600	5	595	4
All providers	claude-fable-5.1	kimi-k3	task_success	40.0%	0.0% to 75.0%	600	5	595	4
All providers	claude-fable-5.1	kimi-k3	decision_correct	0.0%	0.0% to 0.0%	600	5	595	4
All providers	claude-fable-5.1	mimo-v2.6-flash	fact_f1	27.4%	13.8% to 41.8%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-flash	exact_world	42.9%	18.8% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-flash	task_success	42.9%	18.8% to 69.2%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-flash	decision_correct	14.3%	0.0% to 35.7%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-pro	fact_f1	43.5%	26.0% to 58.8%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-pro	exact_world	42.9%	21.4% to 68.8%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-pro	task_success	42.9%	21.4% to 68.8%	600	14	586	13
All providers	claude-fable-5.1	mimo-v2.6-pro	decision_correct	21.4%	0.0% to 42.9%	600	14	586	13
All providers	claude-fable-5.1	minimax-m3	fact_f1	40.0%	19.8% to 58.4%	600	14	586	13
All providers	claude-fable-5.1	minimax-m3	exact_world	35.7%	14.3% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	minimax-m3	task_success	35.7%	14.3% to 61.5%	600	14	586	13
All providers	claude-fable-5.1	minimax-m3	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-fable-5.1	qwen3.8-27b	fact_f1	20.5%	7.8% to 35.1%	600	14	586	13
All providers	claude-fable-5.1	qwen3.8-27b	exact_world	42.9%	21.4% to 68.8%	600	14	586	13
All providers	claude-fable-5.1	qwen3.8-27b	task_success	42.9%	21.4% to 68.8%	600	14	586	13
All providers	claude-fable-5.1	qwen3.8-27b	decision_correct	0.0%	0.0% to 0.0%	600	14	586	13
All providers	claude-haiku-4.5	claude-opus-5	fact_f1	-19.6%	-23.7% to -15.7%	600	424	176	119
All providers	claude-haiku-4.5	claude-opus-5	exact_world	-47.4%	-53.2% to -41.6%	600	424	176	119
All providers	claude-haiku-4.5	claude-opus-5	task_success	-47.4%	-53.2% to -41.6%	600	424	176	119
All providers	claude-haiku-4.5	claude-opus-5	decision_correct	2.8%	-1.2% to 6.7%	600	424	176	119
All providers	claude-haiku-4.5	claude-opus-5.5	fact_f1	-25.0%	-28.0% to -21.9%	600	591	9	120
All providers	claude-haiku-4.5	claude-opus-5.5	exact_world	-16.6%	-20.7% to -12.4%	600	591	9	120
All providers	claude-haiku-4.5	claude-opus-5.5	task_success	-16.4%	-20.5% to -12.2%	600	591	9	120
All providers	claude-haiku-4.5	claude-opus-5.5	decision_correct	0.2%	-2.4% to 2.7%	600	591	9	120
All providers	claude-haiku-4.5	claude-sonnet-5	fact_f1	-17.4%	-20.1% to -14.6%	600	445	155	120
All providers	claude-haiku-4.5	claude-sonnet-5	exact_world	-25.4%	-30.0% to -20.6%	600	445	155	120
All providers	claude-haiku-4.5	claude-sonnet-5	task_success	-25.4%	-30.0% to -20.6%	600	445	155	120
All providers	claude-haiku-4.5	claude-sonnet-5	decision_correct	-0.7%	-3.1% to 1.8%	600	445	155	120
All providers	claude-haiku-4.5	deepseek-4.1-flash	fact_f1	-11.2%	-13.8% to -8.3%	600	595	5	120
All providers	claude-haiku-4.5	deepseek-4.1-flash	exact_world	-25.2%	-29.0% to -21.1%	600	595	5	120
All providers	claude-haiku-4.5	deepseek-4.1-flash	task_success	-25.2%	-29.0% to -21.1%	600	595	5	120
All providers	claude-haiku-4.5	deepseek-4.1-flash	decision_correct	-4.4%	-6.2% to -2.7%	600	595	5	120
All providers	claude-haiku-4.5	deepseek-v4-pro	fact_f1	-23.4%	-26.3% to -20.6%	600	600	0	120
All providers	claude-haiku-4.5	deepseek-v4-pro	exact_world	-19.0%	-22.7% to -15.5%	600	600	0	120
All providers	claude-haiku-4.5	deepseek-v4-pro	task_success	-19.0%	-22.7% to -15.5%	600	600	0	120
All providers	claude-haiku-4.5	deepseek-v4-pro	decision_correct	0.2%	-2.0% to 2.3%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.6-flash	fact_f1	-11.4%	-13.9% to -8.9%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.6-flash	exact_world	-20.0%	-23.7% to -16.3%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.6-flash	task_success	-20.0%	-23.7% to -16.3%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.6-flash	decision_correct	-3.5%	-5.0% to -2.0%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.7-flash	fact_f1	-23.3%	-25.7% to -20.7%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.7-flash	exact_world	-45.0%	-48.8% to -41.2%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.7-flash	task_success	-45.0%	-48.8% to -41.2%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.7-flash	decision_correct	-4.0%	-5.5% to -2.5%	600	600	0	120
All providers	claude-haiku-4.5	gemini-3.8-flash	fact_f1	-18.5%	-20.8% to -16.2%	600	598	2	120
All providers	claude-haiku-4.5	gemini-3.8-flash	exact_world	-35.5%	-39.9% to -31.1%	600	598	2	120
All providers	claude-haiku-4.5	gemini-3.8-flash	task_success	-35.5%	-39.9% to -31.1%	600	598	2	120
All providers	claude-haiku-4.5	gemini-3.8-flash	decision_correct	-4.2%	-5.9% to -2.7%	600	598	2	120
All providers	claude-haiku-4.5	glm-4.7-flash	fact_f1	2.6%	-0.6% to 5.9%	600	566	34	120
All providers	claude-haiku-4.5	glm-4.7-flash	exact_world	4.4%	1.8% to 7.1%	600	566	34	120
All providers	claude-haiku-4.5	glm-4.7-flash	task_success	4.4%	1.8% to 7.1%	600	566	34	120
All providers	claude-haiku-4.5	glm-4.7-flash	decision_correct	14.3%	11.0% to 17.7%	600	566	34	120
All providers	claude-haiku-4.5	glm-5.3	fact_f1	-16.2%	-19.5% to -13.0%	600	564	36	120
All providers	claude-haiku-4.5	glm-5.3	exact_world	-31.9%	-36.5% to -27.9%	600	564	36	120
All providers	claude-haiku-4.5	glm-5.3	task_success	-31.7%	-36.3% to -27.7%	600	564	36	120
All providers	claude-haiku-4.5	glm-5.3	decision_correct	-0.5%	-2.9% to 1.8%	600	564	36	120
All providers	claude-haiku-4.5	glm-5.3-flash	fact_f1	0.9%	-2.0% to 3.9%	600	596	4	120
All providers	claude-haiku-4.5	glm-5.3-flash	exact_world	-2.3%	-5.4% to 0.5%	600	596	4	120
All providers	claude-haiku-4.5	glm-5.3-flash	task_success	-2.2%	-5.2% to 0.7%	600	596	4	120
All providers	claude-haiku-4.5	glm-5.3-flash	decision_correct	-2.9%	-5.2% to -0.7%	600	596	4	120
All providers	claude-haiku-4.5	gpt-5.6-luna	fact_f1	-13.3%	-16.3% to -10.1%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-luna	exact_world	-19.0%	-22.8% to -15.0%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-luna	task_success	-18.0%	-21.8% to -14.2%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-luna	decision_correct	-1.7%	-3.7% to 0.3%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-sol	fact_f1	-23.0%	-25.8% to -20.1%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-sol	exact_world	-44.8%	-49.7% to -39.5%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-sol	task_success	-44.8%	-49.7% to -39.5%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-sol	decision_correct	-4.5%	-6.5% to -2.7%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-terra	fact_f1	-13.7%	-16.5% to -10.8%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-terra	exact_world	-27.0%	-30.7% to -23.0%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-terra	task_success	-27.0%	-30.7% to -23.0%	600	600	0	120
All providers	claude-haiku-4.5	gpt-5.6-terra	decision_correct	-4.3%	-6.2% to -2.7%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-astra	fact_f1	-29.4%	-32.3% to -26.4%	600	550	50	115
All providers	claude-haiku-4.5	gpt-6-astra	exact_world	-62.9%	-67.3% to -58.2%	600	550	50	115
All providers	claude-haiku-4.5	gpt-6-astra	task_success	-62.9%	-67.3% to -58.2%	600	550	50	115
All providers	claude-haiku-4.5	gpt-6-astra	decision_correct	-4.4%	-6.4% to -2.7%	600	550	50	115
All providers	claude-haiku-4.5	gpt-6-luna	fact_f1	-13.4%	-16.4% to -10.4%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-luna	exact_world	-18.8%	-22.8% to -15.2%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-luna	task_success	-18.7%	-22.7% to -15.0%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-luna	decision_correct	-2.8%	-5.2% to -0.7%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-sol	fact_f1	-28.6%	-31.7% to -25.4%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-sol	exact_world	-50.7%	-54.8% to -46.0%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-sol	task_success	-50.5%	-54.7% to -45.8%	600	600	0	120
All providers	claude-haiku-4.5	gpt-6-sol	decision_correct	-3.0%	-4.8% to -1.2%	600	600	0	120
All providers	claude-haiku-4.5	grok-4.6	fact_f1	-21.4%	-24.5% to -18.4%	600	600	0	120
All providers	claude-haiku-4.5	grok-4.6	exact_world	-13.3%	-17.3% to -9.7%	600	600	0	120
All providers	claude-haiku-4.5	grok-4.6	task_success	-13.3%	-17.3% to -9.7%	600	600	0	120
All providers	claude-haiku-4.5	grok-4.6	decision_correct	-1.2%	-3.2% to 0.8%	600	600	0	120
All providers	claude-haiku-4.5	kimi-k2.6	fact_f1	-22.5%	-25.1% to -19.8%	600	599	1	120
All providers	claude-haiku-4.5	kimi-k2.6	exact_world	-12.9%	-16.2% to -9.7%	600	599	1	120
All providers	claude-haiku-4.5	kimi-k2.6	task_success	-12.9%	-16.2% to -9.7%	600	599	1	120
All providers	claude-haiku-4.5	kimi-k2.6	decision_correct	-2.3%	-4.5% to -0.3%	600	599	1	120
All providers	claude-haiku-4.5	kimi-k3	fact_f1	-14.1%	-17.1% to -11.1%	600	443	157	96
All providers	claude-haiku-4.5	kimi-k3	exact_world	-17.2%	-21.5% to -12.7%	600	443	157	96
All providers	claude-haiku-4.5	kimi-k3	task_success	-17.2%	-21.5% to -12.7%	600	443	157	96
All providers	claude-haiku-4.5	kimi-k3	decision_correct	-4.7%	-7.1% to -2.7%	600	443	157	96
All providers	claude-haiku-4.5	mimo-v2.6-flash	fact_f1	-11.4%	-14.1% to -8.6%	600	594	6	120
All providers	claude-haiku-4.5	mimo-v2.6-flash	exact_world	-17.3%	-20.7% to -14.2%	600	594	6	120
All providers	claude-haiku-4.5	mimo-v2.6-flash	task_success	-15.7%	-19.0% to -12.5%	600	594	6	120
All providers	claude-haiku-4.5	mimo-v2.6-flash	decision_correct	5.6%	2.5% to 8.8%	600	594	6	120
All providers	claude-haiku-4.5	mimo-v2.6-pro	fact_f1	-8.6%	-11.3% to -5.6%	600	600	0	120
All providers	claude-haiku-4.5	mimo-v2.6-pro	exact_world	-15.5%	-18.7% to -12.3%	600	600	0	120
All providers	claude-haiku-4.5	mimo-v2.6-pro	task_success	-14.3%	-17.7% to -10.8%	600	600	0	120
All providers	claude-haiku-4.5	mimo-v2.6-pro	decision_correct	7.0%	3.3% to 10.7%	600	600	0	120
All providers	claude-haiku-4.5	minimax-m3	fact_f1	-0.4%	-3.5% to 2.8%	600	600	0	120
All providers	claude-haiku-4.5	minimax-m3	exact_world	-10.2%	-13.5% to -6.8%	600	600	0	120
All providers	claude-haiku-4.5	minimax-m3	task_success	-10.2%	-13.5% to -6.8%	600	600	0	120
All providers	claude-haiku-4.5	minimax-m3	decision_correct	-1.2%	-3.0% to 0.7%	600	600	0	120
All providers	claude-haiku-4.5	qwen3.8-27b	fact_f1	-15.6%	-18.2% to -12.8%	600	600	0	120
All providers	claude-haiku-4.5	qwen3.8-27b	exact_world	-10.0%	-13.7% to -6.3%	600	600	0	120
All providers	claude-haiku-4.5	qwen3.8-27b	task_success	-10.0%	-13.7% to -6.3%	600	600	0	120
All providers	claude-haiku-4.5	qwen3.8-27b	decision_correct	-1.5%	-3.5% to 0.5%	600	600	0	120
All providers	claude-opus-5	claude-opus-5.5	fact_f1	-10.5%	-13.8% to -7.2%	600	416	184	119
All providers	claude-opus-5	claude-opus-5.5	exact_world	27.2%	20.8% to 33.2%	600	416	184	119
All providers	claude-opus-5	claude-opus-5.5	task_success	27.4%	21.0% to 33.5%	600	416	184	119
All providers	claude-opus-5	claude-opus-5.5	decision_correct	-2.6%	-6.2% to 0.8%	600	416	184	119
All providers	claude-opus-5	claude-sonnet-5	fact_f1	-6.6%	-11.0% to -2.4%	600	314	286	106
All providers	claude-opus-5	claude-sonnet-5	exact_world	11.5%	3.4% to 19.4%	600	314	286	106
All providers	claude-opus-5	claude-sonnet-5	task_success	11.5%	3.4% to 19.4%	600	314	286	106
All providers	claude-opus-5	claude-sonnet-5	decision_correct	-4.8%	-8.8% to -0.9%	600	314	286	106
All providers	claude-opus-5	deepseek-4.1-flash	fact_f1	5.4%	1.7% to 9.2%	600	419	181	119
All providers	claude-opus-5	deepseek-4.1-flash	exact_world	14.1%	7.1% to 21.2%	600	419	181	119
All providers	claude-opus-5	deepseek-4.1-flash	task_success	14.1%	7.1% to 21.2%	600	419	181	119
All providers	claude-opus-5	deepseek-4.1-flash	decision_correct	-8.4%	-11.1% to -5.7%	600	419	181	119
All providers	claude-opus-5	deepseek-v4-pro	fact_f1	-9.0%	-12.4% to -5.7%	600	424	176	119
All providers	claude-opus-5	deepseek-v4-pro	exact_world	22.2%	15.3% to 28.8%	600	424	176	119
All providers	claude-opus-5	deepseek-v4-pro	task_success	22.2%	15.3% to 28.8%	600	424	176	119
All providers	claude-opus-5	deepseek-v4-pro	decision_correct	-3.5%	-6.7% to -0.2%	600	424	176	119
All providers	claude-opus-5	gemini-3.6-flash	fact_f1	6.3%	2.2% to 10.6%	600	424	176	119
All providers	claude-opus-5	gemini-3.6-flash	exact_world	21.0%	13.5% to 28.3%	600	424	176	119
All providers	claude-opus-5	gemini-3.6-flash	task_success	21.0%	13.5% to 28.3%	600	424	176	119
All providers	claude-opus-5	gemini-3.6-flash	decision_correct	-7.3%	-10.3% to -4.1%	600	424	176	119
All providers	claude-opus-5	gemini-3.7-flash	fact_f1	-8.8%	-12.2% to -5.2%	600	424	176	119
All providers	claude-opus-5	gemini-3.7-flash	exact_world	-9.0%	-15.9% to -2.1%	600	424	176	119
All providers	claude-opus-5	gemini-3.7-flash	task_success	-9.0%	-15.9% to -2.1%	600	424	176	119
All providers	claude-opus-5	gemini-3.7-flash	decision_correct	-7.8%	-10.7% to -4.8%	600	424	176	119
All providers	claude-opus-5	gemini-3.8-flash	fact_f1	-3.6%	-6.9% to -0.2%	600	422	178	119
All providers	claude-opus-5	gemini-3.8-flash	exact_world	1.4%	-5.8% to 8.7%	600	422	178	119
All providers	claude-opus-5	gemini-3.8-flash	task_success	1.4%	-5.8% to 8.7%	600	422	178	119
All providers	claude-opus-5	gemini-3.8-flash	decision_correct	-8.1%	-11.0% to -5.2%	600	422	178	119
All providers	claude-opus-5	glm-4.7-flash	fact_f1	19.6%	15.2% to 24.2%	600	393	207	118
All providers	claude-opus-5	glm-4.7-flash	exact_world	47.3%	41.4% to 53.3%	600	393	207	118
All providers	claude-opus-5	glm-4.7-flash	task_success	47.3%	41.4% to 53.3%	600	393	207	118
All providers	claude-opus-5	glm-4.7-flash	decision_correct	11.2%	6.0% to 16.4%	600	393	207	118
All providers	claude-opus-5	glm-5.3	fact_f1	-1.2%	-5.5% to 3.0%	600	390	210	118
All providers	claude-opus-5	glm-5.3	exact_world	6.4%	-1.3% to 13.9%	600	390	210	118
All providers	claude-opus-5	glm-5.3	task_success	6.7%	-1.0% to 14.0%	600	390	210	118
All providers	claude-opus-5	glm-5.3	decision_correct	-4.1%	-7.6% to -0.5%	600	390	210	118
All providers	claude-opus-5	glm-5.3-flash	fact_f1	20.9%	16.0% to 25.9%	600	420	180	119
All providers	claude-opus-5	glm-5.3-flash	exact_world	40.0%	33.5% to 46.5%	600	420	180	119
All providers	claude-opus-5	glm-5.3-flash	task_success	40.2%	33.6% to 46.7%	600	420	180	119
All providers	claude-opus-5	glm-5.3-flash	decision_correct	-6.4%	-9.6% to -3.3%	600	420	180	119
All providers	claude-opus-5	gpt-5.6-luna	fact_f1	2.4%	-1.0% to 5.8%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-luna	exact_world	22.6%	16.1% to 29.0%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-luna	task_success	23.6%	17.2% to 30.3%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-luna	decision_correct	-5.7%	-8.9% to -2.3%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-sol	fact_f1	-8.4%	-11.6% to -5.3%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-sol	exact_world	-8.7%	-15.8% to -1.7%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-sol	task_success	-8.7%	-15.8% to -1.7%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-sol	decision_correct	-8.5%	-11.4% to -5.9%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-terra	fact_f1	2.1%	-1.5% to 5.9%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-terra	exact_world	12.7%	6.5% to 19.1%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-terra	task_success	12.7%	6.5% to 19.1%	600	424	176	119
All providers	claude-opus-5	gpt-5.6-terra	decision_correct	-8.3%	-11.1% to -5.5%	600	424	176	119
All providers	claude-opus-5	gpt-6-astra	fact_f1	-16.7%	-20.1% to -13.5%	600	386	214	111
All providers	claude-opus-5	gpt-6-astra	exact_world	-32.1%	-39.0% to -25.1%	600	386	214	111
All providers	claude-opus-5	gpt-6-astra	task_success	-32.1%	-39.0% to -25.1%	600	386	214	111
All providers	claude-opus-5	gpt-6-astra	decision_correct	-7.8%	-10.7% to -5.2%	600	386	214	111
All providers	claude-opus-5	gpt-6-luna	fact_f1	3.6%	-0.4% to 7.5%	600	424	176	119
All providers	claude-opus-5	gpt-6-luna	exact_world	24.8%	18.1% to 31.7%	600	424	176	119
All providers	claude-opus-5	gpt-6-luna	task_success	24.8%	18.1% to 31.7%	600	424	176	119
All providers	claude-opus-5	gpt-6-luna	decision_correct	-6.4%	-9.6% to -3.1%	600	424	176	119
All providers	claude-opus-5	gpt-6-sol	fact_f1	-15.1%	-18.5% to -11.7%	600	424	176	119
All providers	claude-opus-5	gpt-6-sol	exact_world	-16.0%	-22.9% to -8.9%	600	424	176	119
All providers	claude-opus-5	gpt-6-sol	task_success	-15.8%	-22.7% to -8.8%	600	424	176	119
All providers	claude-opus-5	gpt-6-sol	decision_correct	-6.8%	-9.9% to -3.9%	600	424	176	119
All providers	claude-opus-5	grok-4.6	fact_f1	-6.2%	-9.7% to -2.4%	600	424	176	119
All providers	claude-opus-5	grok-4.6	exact_world	30.7%	24.4% to 36.8%	600	424	176	119
All providers	claude-opus-5	grok-4.6	task_success	30.7%	24.4% to 36.8%	600	424	176	119
All providers	claude-opus-5	grok-4.6	decision_correct	-4.7%	-8.4% to -0.7%	600	424	176	119
All providers	claude-opus-5	kimi-k2.6	fact_f1	-7.5%	-10.8% to -4.4%	600	423	177	119
All providers	claude-opus-5	kimi-k2.6	exact_world	30.7%	24.0% to 37.7%	600	423	177	119
All providers	claude-opus-5	kimi-k2.6	task_success	30.7%	24.0% to 37.7%	600	423	177	119
All providers	claude-opus-5	kimi-k2.6	decision_correct	-6.4%	-9.5% to -3.5%	600	423	177	119
All providers	claude-opus-5	kimi-k3	fact_f1	-0.1%	-4.1% to 4.0%	600	310	290	94
All providers	claude-opus-5	kimi-k3	exact_world	24.2%	16.2% to 32.6%	600	310	290	94
All providers	claude-opus-5	kimi-k3	task_success	24.2%	16.2% to 32.6%	600	310	290	94
All providers	claude-opus-5	kimi-k3	decision_correct	-7.1%	-10.5% to -4.1%	600	310	290	94
All providers	claude-opus-5	mimo-v2.6-flash	fact_f1	4.3%	0.4% to 8.1%	600	418	182	119
All providers	claude-opus-5	mimo-v2.6-flash	exact_world	23.4%	17.3% to 29.8%	600	418	182	119
All providers	claude-opus-5	mimo-v2.6-flash	task_success	24.9%	18.4% to 31.3%	600	418	182	119
All providers	claude-opus-5	mimo-v2.6-flash	decision_correct	1.9%	-2.0% to 6.0%	600	418	182	119
All providers	claude-opus-5	mimo-v2.6-pro	fact_f1	7.9%	3.8% to 11.9%	600	424	176	119
All providers	claude-opus-5	mimo-v2.6-pro	exact_world	25.5%	19.2% to 32.1%	600	424	176	119
All providers	claude-opus-5	mimo-v2.6-pro	task_success	26.7%	20.2% to 33.4%	600	424	176	119
All providers	claude-opus-5	mimo-v2.6-pro	decision_correct	5.9%	1.7% to 10.3%	600	424	176	119
All providers	claude-opus-5	minimax-m3	fact_f1	19.3%	14.4% to 24.0%	600	424	176	119
All providers	claude-opus-5	minimax-m3	exact_world	34.0%	27.4% to 40.5%	600	424	176	119
All providers	claude-opus-5	minimax-m3	task_success	34.0%	27.4% to 40.5%	600	424	176	119
All providers	claude-opus-5	minimax-m3	decision_correct	-4.7%	-8.3% to -1.1%	600	424	176	119
All providers	claude-opus-5	qwen3.8-27b	fact_f1	-0.3%	-4.3% to 3.7%	600	424	176	119
All providers	claude-opus-5	qwen3.8-27b	exact_world	32.5%	26.0% to 39.3%	600	424	176	119
All providers	claude-opus-5	qwen3.8-27b	task_success	32.5%	26.0% to 39.3%	600	424	176	119
All providers	claude-opus-5	qwen3.8-27b	decision_correct	-5.7%	-8.9% to -2.2%	600	424	176	119
All providers	claude-opus-5.5	claude-sonnet-5	fact_f1	3.9%	1.6% to 6.2%	600	441	159	120
All providers	claude-opus-5.5	claude-sonnet-5	exact_world	-12.2%	-17.8% to -5.9%	600	441	159	120
All providers	claude-opus-5.5	claude-sonnet-5	task_success	-12.5%	-17.9% to -6.3%	600	441	159	120
All providers	claude-opus-5.5	claude-sonnet-5	decision_correct	-0.2%	-2.9% to 2.3%	600	441	159	120
All providers	claude-opus-5.5	deepseek-4.1-flash	fact_f1	13.8%	11.4% to 16.1%	600	586	14	120
All providers	claude-opus-5.5	deepseek-4.1-flash	exact_world	-8.4%	-13.6% to -3.1%	600	586	14	120
All providers	claude-opus-5.5	deepseek-4.1-flash	task_success	-8.5%	-13.8% to -3.4%	600	586	14	120
All providers	claude-opus-5.5	deepseek-4.1-flash	decision_correct	-4.4%	-6.5% to -2.7%	600	586	14	120
All providers	claude-opus-5.5	deepseek-v4-pro	fact_f1	1.8%	0.3% to 3.3%	600	591	9	120
All providers	claude-opus-5.5	deepseek-v4-pro	exact_world	-2.2%	-7.8% to 3.2%	600	591	9	120
All providers	claude-opus-5.5	deepseek-v4-pro	task_success	-2.4%	-8.0% to 3.0%	600	591	9	120
All providers	claude-opus-5.5	deepseek-v4-pro	decision_correct	-0.3%	-2.5% to 1.8%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.6-flash	fact_f1	13.8%	11.0% to 16.6%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.6-flash	exact_world	-2.9%	-8.9% to 3.1%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.6-flash	task_success	-3.0%	-9.1% to 2.9%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.6-flash	decision_correct	-3.7%	-5.9% to -1.7%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.7-flash	fact_f1	1.9%	0.1% to 3.8%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.7-flash	exact_world	-28.3%	-33.3% to -23.3%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.7-flash	task_success	-28.4%	-33.4% to -23.6%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.7-flash	decision_correct	-4.2%	-6.3% to -2.4%	600	591	9	120
All providers	claude-opus-5.5	gemini-3.8-flash	fact_f1	6.6%	4.4% to 8.7%	600	589	11	120
All providers	claude-opus-5.5	gemini-3.8-flash	exact_world	-18.8%	-24.0% to -13.7%	600	589	11	120
All providers	claude-opus-5.5	gemini-3.8-flash	task_success	-19.0%	-24.1% to -13.9%	600	589	11	120
All providers	claude-opus-5.5	gemini-3.8-flash	decision_correct	-4.4%	-6.5% to -2.6%	600	589	11	120
All providers	claude-opus-5.5	glm-4.7-flash	fact_f1	26.1%	23.2% to 28.9%	600	557	43	120
All providers	claude-opus-5.5	glm-4.7-flash	exact_world	20.5%	15.8% to 25.2%	600	557	43	120
All providers	claude-opus-5.5	glm-4.7-flash	task_success	20.3%	15.6% to 25.0%	600	557	43	120
All providers	claude-opus-5.5	glm-4.7-flash	decision_correct	13.3%	9.5% to 17.0%	600	557	43	120
All providers	claude-opus-5.5	glm-5.3	fact_f1	7.9%	4.9% to 11.1%	600	556	44	120
All providers	claude-opus-5.5	glm-5.3	exact_world	-15.3%	-21.8% to -9.2%	600	556	44	120
All providers	claude-opus-5.5	glm-5.3	task_success	-15.3%	-21.9% to -9.2%	600	556	44	120
All providers	claude-opus-5.5	glm-5.3	decision_correct	-1.3%	-4.0% to 1.4%	600	556	44	120
All providers	claude-opus-5.5	glm-5.3-flash	fact_f1	26.0%	22.4% to 29.4%	600	588	12	120
All providers	claude-opus-5.5	glm-5.3-flash	exact_world	14.5%	9.5% to 19.3%	600	588	12	120
All providers	claude-opus-5.5	glm-5.3-flash	task_success	14.5%	9.6% to 19.2%	600	588	12	120
All providers	claude-opus-5.5	glm-5.3-flash	decision_correct	-3.1%	-5.4% to -0.8%	600	588	12	120
All providers	claude-opus-5.5	gpt-5.6-luna	fact_f1	11.7%	9.6% to 13.8%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-luna	exact_world	-2.2%	-7.1% to 2.9%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-luna	task_success	-1.4%	-6.1% to 3.9%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-luna	decision_correct	-2.0%	-4.3% to 0.2%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-sol	fact_f1	2.1%	0.2% to 4.1%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-sol	exact_world	-27.9%	-33.6% to -22.5%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-sol	task_success	-28.1%	-33.7% to -22.7%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-sol	decision_correct	-4.7%	-6.9% to -2.9%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-terra	fact_f1	11.6%	9.3% to 13.8%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-terra	exact_world	-10.0%	-14.9% to -5.4%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-terra	task_success	-10.2%	-15.0% to -5.6%	600	591	9	120
All providers	claude-opus-5.5	gpt-5.6-terra	decision_correct	-4.6%	-6.6% to -2.7%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-astra	fact_f1	-5.3%	-6.1% to -4.5%	600	542	58	115
All providers	claude-opus-5.5	gpt-6-astra	exact_world	-46.7%	-51.1% to -41.8%	600	542	58	115
All providers	claude-opus-5.5	gpt-6-astra	task_success	-46.9%	-51.3% to -42.1%	600	542	58	115
All providers	claude-opus-5.5	gpt-6-astra	decision_correct	-4.8%	-7.0% to -2.9%	600	542	58	115
All providers	claude-opus-5.5	gpt-6-luna	fact_f1	11.7%	9.4% to 14.0%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-luna	exact_world	-2.5%	-7.5% to 2.0%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-luna	task_success	-2.5%	-7.6% to 2.0%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-luna	decision_correct	-3.2%	-5.4% to -1.2%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-sol	fact_f1	-3.4%	-4.5% to -2.3%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-sol	exact_world	-33.8%	-38.7% to -29.1%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-sol	task_success	-33.8%	-38.7% to -29.1%	600	591	9	120
All providers	claude-opus-5.5	gpt-6-sol	decision_correct	-3.2%	-5.2% to -1.4%	600	591	9	120
All providers	claude-opus-5.5	grok-4.6	fact_f1	3.8%	2.6% to 5.0%	600	591	9	120
All providers	claude-opus-5.5	grok-4.6	exact_world	3.7%	-0.3% to 7.8%	600	591	9	120
All providers	claude-opus-5.5	grok-4.6	task_success	3.6%	-0.5% to 7.6%	600	591	9	120
All providers	claude-opus-5.5	grok-4.6	decision_correct	-1.4%	-3.7% to 1.0%	600	591	9	120
All providers	claude-opus-5.5	kimi-k2.6	fact_f1	2.7%	1.4% to 4.1%	600	591	9	120
All providers	claude-opus-5.5	kimi-k2.6	exact_world	3.7%	-1.4% to 8.6%	600	591	9	120
All providers	claude-opus-5.5	kimi-k2.6	task_success	3.6%	-1.7% to 8.4%	600	591	9	120
All providers	claude-opus-5.5	kimi-k2.6	decision_correct	-2.7%	-5.1% to -0.5%	600	591	9	120
All providers	claude-opus-5.5	kimi-k3	fact_f1	8.3%	5.3% to 11.2%	600	438	162	96
All providers	claude-opus-5.5	kimi-k3	exact_world	-2.1%	-8.1% to 4.0%	600	438	162	96
All providers	claude-opus-5.5	kimi-k3	task_success	-2.3%	-8.3% to 3.6%	600	438	162	96
All providers	claude-opus-5.5	kimi-k3	decision_correct	-4.6%	-6.9% to -2.5%	600	438	162	96
All providers	claude-opus-5.5	mimo-v2.6-flash	fact_f1	14.1%	11.6% to 16.6%	600	585	15	120
All providers	claude-opus-5.5	mimo-v2.6-flash	exact_world	-0.7%	-5.6% to 4.0%	600	585	15	120
All providers	claude-opus-5.5	mimo-v2.6-flash	task_success	0.9%	-4.1% to 5.3%	600	585	15	120
All providers	claude-opus-5.5	mimo-v2.6-flash	decision_correct	5.6%	2.2% to 9.0%	600	585	15	120
All providers	claude-opus-5.5	mimo-v2.6-pro	fact_f1	16.5%	14.0% to 19.2%	600	591	9	120
All providers	claude-opus-5.5	mimo-v2.6-pro	exact_world	1.2%	-3.7% to 6.0%	600	591	9	120
All providers	claude-opus-5.5	mimo-v2.6-pro	task_success	2.2%	-2.9% to 7.1%	600	591	9	120
All providers	claude-opus-5.5	mimo-v2.6-pro	decision_correct	6.9%	3.4% to 10.6%	600	591	9	120
All providers	claude-opus-5.5	minimax-m3	fact_f1	24.7%	21.4% to 28.0%	600	591	9	120
All providers	claude-opus-5.5	minimax-m3	exact_world	6.6%	1.7% to 11.7%	600	591	9	120
All providers	claude-opus-5.5	minimax-m3	task_success	6.4%	1.5% to 11.5%	600	591	9	120
All providers	claude-opus-5.5	minimax-m3	decision_correct	-1.4%	-3.7% to 0.8%	600	591	9	120
All providers	claude-opus-5.5	qwen3.8-27b	fact_f1	9.5%	7.4% to 11.8%	600	591	9	120
All providers	claude-opus-5.5	qwen3.8-27b	exact_world	6.8%	1.3% to 12.3%	600	591	9	120
All providers	claude-opus-5.5	qwen3.8-27b	task_success	6.6%	1.0% to 12.2%	600	591	9	120
All providers	claude-opus-5.5	qwen3.8-27b	decision_correct	-1.7%	-3.9% to 0.5%	600	591	9	120
All providers	claude-sonnet-5	deepseek-4.1-flash	fact_f1	5.0%	2.1% to 7.7%	600	440	160	120
All providers	claude-sonnet-5	deepseek-4.1-flash	exact_world	-0.7%	-5.8% to 4.5%	600	440	160	120
All providers	claude-sonnet-5	deepseek-4.1-flash	task_success	-0.7%	-5.8% to 4.5%	600	440	160	120
All providers	claude-sonnet-5	deepseek-4.1-flash	decision_correct	-4.1%	-6.0% to -2.3%	600	440	160	120
All providers	claude-sonnet-5	deepseek-v4-pro	fact_f1	-1.9%	-4.4% to 0.5%	600	445	155	120
All providers	claude-sonnet-5	deepseek-v4-pro	exact_world	7.9%	2.4% to 13.2%	600	445	155	120
All providers	claude-sonnet-5	deepseek-v4-pro	task_success	7.9%	2.4% to 13.2%	600	445	155	120
All providers	claude-sonnet-5	deepseek-v4-pro	decision_correct	0.7%	-1.8% to 3.4%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.6-flash	fact_f1	7.9%	5.0% to 10.8%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.6-flash	exact_world	4.3%	-1.6% to 9.7%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.6-flash	task_success	4.3%	-1.6% to 9.7%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.6-flash	decision_correct	-3.1%	-4.9% to -1.6%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.7-flash	fact_f1	-3.4%	-5.6% to -1.2%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.7-flash	exact_world	-16.9%	-22.0% to -12.1%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.7-flash	task_success	-16.9%	-22.0% to -12.1%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.7-flash	decision_correct	-3.4%	-5.0% to -1.9%	600	445	155	120
All providers	claude-sonnet-5	gemini-3.8-flash	fact_f1	0.7%	-1.7% to 3.0%	600	443	157	120
All providers	claude-sonnet-5	gemini-3.8-flash	exact_world	-9.3%	-14.4% to -4.6%	600	443	157	120
All providers	claude-sonnet-5	gemini-3.8-flash	task_success	-9.3%	-14.4% to -4.6%	600	443	157	120
All providers	claude-sonnet-5	gemini-3.8-flash	decision_correct	-3.6%	-5.3% to -2.0%	600	443	157	120
All providers	claude-sonnet-5	glm-4.7-flash	fact_f1	22.8%	19.2% to 26.2%	600	415	185	120
All providers	claude-sonnet-5	glm-4.7-flash	exact_world	31.6%	26.1% to 36.6%	600	415	185	120
All providers	claude-sonnet-5	glm-4.7-flash	task_success	31.6%	26.1% to 36.6%	600	415	185	120
All providers	claude-sonnet-5	glm-4.7-flash	decision_correct	13.3%	9.3% to 17.6%	600	415	185	120
All providers	claude-sonnet-5	glm-5.3	fact_f1	3.7%	0.4% to 7.2%	600	421	179	120
All providers	claude-sonnet-5	glm-5.3	exact_world	-3.8%	-9.5% to 1.0%	600	421	179	120
All providers	claude-sonnet-5	glm-5.3	task_success	-3.6%	-9.3% to 1.4%	600	421	179	120
All providers	claude-sonnet-5	glm-5.3	decision_correct	-1.0%	-3.2% to 1.2%	600	421	179	120
All providers	claude-sonnet-5	glm-5.3-flash	fact_f1	18.5%	14.9% to 21.9%	600	441	159	120
All providers	claude-sonnet-5	glm-5.3-flash	exact_world	23.1%	17.6% to 28.3%	600	441	159	120
All providers	claude-sonnet-5	glm-5.3-flash	task_success	23.4%	18.0% to 28.5%	600	441	159	120
All providers	claude-sonnet-5	glm-5.3-flash	decision_correct	-2.5%	-4.6% to -0.4%	600	441	159	120
All providers	claude-sonnet-5	gpt-5.6-luna	fact_f1	3.9%	0.9% to 6.7%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-luna	exact_world	5.6%	0.0% to 10.8%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-luna	task_success	7.0%	1.4% to 12.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-luna	decision_correct	-1.1%	-3.3% to 0.9%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-sol	fact_f1	-3.6%	-6.2% to -1.2%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-sol	exact_world	-16.0%	-22.6% to -9.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-sol	task_success	-16.0%	-22.6% to -9.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-sol	decision_correct	-4.0%	-5.9% to -2.3%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-terra	fact_f1	4.0%	1.5% to 6.5%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-terra	exact_world	0.0%	-5.6% to 5.2%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-terra	task_success	0.0%	-5.6% to 5.2%	600	445	155	120
All providers	claude-sonnet-5	gpt-5.6-terra	decision_correct	-3.8%	-5.6% to -2.2%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-astra	fact_f1	-8.1%	-10.4% to -5.9%	600	407	193	114
All providers	claude-sonnet-5	gpt-6-astra	exact_world	-32.7%	-38.9% to -26.0%	600	407	193	114
All providers	claude-sonnet-5	gpt-6-astra	task_success	-32.7%	-38.9% to -26.0%	600	407	193	114
All providers	claude-sonnet-5	gpt-6-astra	decision_correct	-4.4%	-6.4% to -2.6%	600	407	193	114
All providers	claude-sonnet-5	gpt-6-luna	fact_f1	5.5%	3.0% to 8.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-luna	exact_world	9.9%	4.7% to 14.8%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-luna	task_success	10.1%	4.9% to 15.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-luna	decision_correct	-2.2%	-4.4% to 0.0%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-sol	fact_f1	-6.8%	-9.2% to -4.5%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-sol	exact_world	-20.7%	-27.7% to -13.8%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-sol	task_success	-20.4%	-27.5% to -13.5%	600	445	155	120
All providers	claude-sonnet-5	gpt-6-sol	decision_correct	-2.2%	-4.3% to -0.2%	600	445	155	120
All providers	claude-sonnet-5	grok-4.6	fact_f1	-1.0%	-3.4% to 1.3%	600	445	155	120
All providers	claude-sonnet-5	grok-4.6	exact_world	11.7%	5.6% to 17.2%	600	445	155	120
All providers	claude-sonnet-5	grok-4.6	task_success	11.7%	5.6% to 17.2%	600	445	155	120
All providers	claude-sonnet-5	grok-4.6	decision_correct	-0.7%	-2.9% to 1.7%	600	445	155	120
All providers	claude-sonnet-5	kimi-k2.6	fact_f1	-1.7%	-4.0% to 0.5%	600	444	156	120
All providers	claude-sonnet-5	kimi-k2.6	exact_world	13.7%	8.1% to 18.6%	600	444	156	120
All providers	claude-sonnet-5	kimi-k2.6	task_success	13.7%	8.1% to 18.6%	600	444	156	120
All providers	claude-sonnet-5	kimi-k2.6	decision_correct	-1.8%	-4.2% to 0.7%	600	444	156	120
All providers	claude-sonnet-5	kimi-k3	fact_f1	2.6%	-0.3% to 5.6%	600	329	271	95
All providers	claude-sonnet-5	kimi-k3	exact_world	9.1%	3.2% to 15.0%	600	329	271	95
All providers	claude-sonnet-5	kimi-k3	task_success	9.1%	3.2% to 15.0%	600	329	271	95
All providers	claude-sonnet-5	kimi-k3	decision_correct	-4.3%	-6.3% to -2.4%	600	329	271	95
All providers	claude-sonnet-5	mimo-v2.6-flash	fact_f1	7.8%	5.0% to 10.6%	600	440	160	120
All providers	claude-sonnet-5	mimo-v2.6-flash	exact_world	7.7%	2.3% to 13.0%	600	440	160	120
All providers	claude-sonnet-5	mimo-v2.6-flash	task_success	9.5%	4.2% to 14.4%	600	440	160	120
All providers	claude-sonnet-5	mimo-v2.6-flash	decision_correct	6.6%	3.4% to 10.0%	600	440	160	120
All providers	claude-sonnet-5	mimo-v2.6-pro	fact_f1	9.9%	6.7% to 13.0%	600	445	155	120
All providers	claude-sonnet-5	mimo-v2.6-pro	exact_world	11.0%	5.3% to 16.4%	600	445	155	120
All providers	claude-sonnet-5	mimo-v2.6-pro	task_success	12.1%	6.2% to 17.6%	600	445	155	120
All providers	claude-sonnet-5	mimo-v2.6-pro	decision_correct	7.6%	3.9% to 11.6%	600	445	155	120
All providers	claude-sonnet-5	minimax-m3	fact_f1	16.4%	13.0% to 19.8%	600	445	155	120
All providers	claude-sonnet-5	minimax-m3	exact_world	14.6%	9.8% to 19.3%	600	445	155	120
All providers	claude-sonnet-5	minimax-m3	task_success	14.6%	9.8% to 19.3%	600	445	155	120
All providers	claude-sonnet-5	minimax-m3	decision_correct	-1.1%	-3.3% to 0.9%	600	445	155	120
All providers	claude-sonnet-5	qwen3.8-27b	fact_f1	4.6%	1.6% to 7.4%	600	445	155	120
All providers	claude-sonnet-5	qwen3.8-27b	exact_world	14.8%	9.6% to 19.7%	600	445	155	120
All providers	claude-sonnet-5	qwen3.8-27b	task_success	14.8%	9.6% to 19.7%	600	445	155	120
All providers	claude-sonnet-5	qwen3.8-27b	decision_correct	-0.2%	-2.5% to 2.2%	600	445	155	120
All providers	deepseek-4.1-flash	deepseek-v4-pro	fact_f1	-12.1%	-14.6% to -9.7%	600	595	5	120
All providers	deepseek-4.1-flash	deepseek-v4-pro	exact_world	6.4%	2.0% to 10.7%	600	595	5	120
All providers	deepseek-4.1-flash	deepseek-v4-pro	task_success	6.4%	2.0% to 10.7%	600	595	5	120
All providers	deepseek-4.1-flash	deepseek-v4-pro	decision_correct	4.7%	2.9% to 6.7%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.6-flash	fact_f1	-0.2%	-2.6% to 2.0%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.6-flash	exact_world	5.4%	0.7% to 10.0%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.6-flash	task_success	5.4%	0.7% to 10.0%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.6-flash	decision_correct	0.8%	0.2% to 1.7%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.7-flash	fact_f1	-12.3%	-14.7% to -10.0%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.7-flash	exact_world	-20.0%	-25.0% to -15.1%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.7-flash	task_success	-20.0%	-25.0% to -15.1%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.7-flash	decision_correct	0.3%	0.0% to 0.8%	600	595	5	120
All providers	deepseek-4.1-flash	gemini-3.8-flash	fact_f1	-7.2%	-9.2% to -5.2%	600	593	7	120
All providers	deepseek-4.1-flash	gemini-3.8-flash	exact_world	-10.3%	-15.1% to -5.6%	600	593	7	120
All providers	deepseek-4.1-flash	gemini-3.8-flash	task_success	-10.3%	-15.1% to -5.6%	600	593	7	120
All providers	deepseek-4.1-flash	gemini-3.8-flash	decision_correct	0.2%	0.0% to 0.5%	600	593	7	120
All providers	deepseek-4.1-flash	glm-4.7-flash	fact_f1	12.3%	9.1% to 15.6%	600	563	37	120
All providers	deepseek-4.1-flash	glm-4.7-flash	exact_world	29.7%	25.0% to 34.2%	600	563	37	120
All providers	deepseek-4.1-flash	glm-4.7-flash	task_success	29.7%	25.0% to 34.2%	600	563	37	120
All providers	deepseek-4.1-flash	glm-4.7-flash	decision_correct	17.6%	14.2% to 21.0%	600	563	37	120
All providers	deepseek-4.1-flash	glm-5.3	fact_f1	-6.0%	-8.9% to -3.2%	600	559	41	120
All providers	deepseek-4.1-flash	glm-5.3	exact_world	-7.5%	-12.5% to -2.8%	600	559	41	120
All providers	deepseek-4.1-flash	glm-5.3	task_success	-7.3%	-12.3% to -2.6%	600	559	41	120
All providers	deepseek-4.1-flash	glm-5.3	decision_correct	3.8%	2.3% to 5.4%	600	559	41	120
All providers	deepseek-4.1-flash	glm-5.3-flash	fact_f1	12.0%	9.2% to 14.7%	600	591	9	120
All providers	deepseek-4.1-flash	glm-5.3-flash	exact_world	22.5%	18.3% to 26.8%	600	591	9	120
All providers	deepseek-4.1-flash	glm-5.3-flash	task_success	22.7%	18.4% to 26.9%	600	591	9	120
All providers	deepseek-4.1-flash	glm-5.3-flash	decision_correct	1.5%	0.7% to 2.5%	600	591	9	120
All providers	deepseek-4.1-flash	gpt-5.6-luna	fact_f1	-1.9%	-4.7% to 0.9%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-luna	exact_world	6.7%	1.9% to 11.6%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-luna	task_success	7.7%	2.9% to 12.6%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-luna	decision_correct	2.9%	1.5% to 4.3%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-sol	fact_f1	-11.6%	-14.0% to -9.3%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-sol	exact_world	-19.2%	-25.0% to -13.2%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-sol	task_success	-19.2%	-25.0% to -13.2%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-sol	decision_correct	0.0%	0.0% to 0.0%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-terra	fact_f1	-2.4%	-4.8% to 0.0%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-terra	exact_world	-1.5%	-6.2% to 3.0%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-terra	task_success	-1.5%	-6.2% to 3.0%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-5.6-terra	decision_correct	0.2%	0.0% to 0.5%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-astra	fact_f1	-17.9%	-20.4% to -15.5%	600	545	55	115
All providers	deepseek-4.1-flash	gpt-6-astra	exact_world	-36.0%	-41.5% to -30.1%	600	545	55	115
All providers	deepseek-4.1-flash	gpt-6-astra	task_success	-36.0%	-41.5% to -30.1%	600	545	55	115
All providers	deepseek-4.1-flash	gpt-6-astra	decision_correct	0.0%	0.0% to 0.0%	600	545	55	115
All providers	deepseek-4.1-flash	gpt-6-luna	fact_f1	-2.1%	-5.0% to 0.6%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-luna	exact_world	6.6%	1.3% to 11.4%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-luna	task_success	6.7%	1.5% to 11.5%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-luna	decision_correct	1.7%	0.7% to 2.7%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-sol	fact_f1	-17.3%	-19.8% to -14.7%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-sol	exact_world	-25.4%	-30.7% to -19.9%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-sol	task_success	-25.2%	-30.6% to -19.7%	600	595	5	120
All providers	deepseek-4.1-flash	gpt-6-sol	decision_correct	1.3%	0.5% to 2.3%	600	595	5	120
All providers	deepseek-4.1-flash	grok-4.6	fact_f1	-10.2%	-12.7% to -7.7%	600	595	5	120
All providers	deepseek-4.1-flash	grok-4.6	exact_world	11.9%	7.1% to 16.7%	600	595	5	120
All providers	deepseek-4.1-flash	grok-4.6	task_success	11.9%	7.1% to 16.7%	600	595	5	120
All providers	deepseek-4.1-flash	grok-4.6	decision_correct	3.2%	1.3% to 5.2%	600	595	5	120
All providers	deepseek-4.1-flash	kimi-k2.6	fact_f1	-11.2%	-13.4% to -9.0%	600	594	6	120
All providers	deepseek-4.1-flash	kimi-k2.6	exact_world	12.3%	7.9% to 16.5%	600	594	6	120
All providers	deepseek-4.1-flash	kimi-k2.6	task_success	12.3%	7.9% to 16.5%	600	594	6	120
All providers	deepseek-4.1-flash	kimi-k2.6	decision_correct	2.2%	1.0% to 3.6%	600	594	6	120
All providers	deepseek-4.1-flash	kimi-k3	fact_f1	-2.8%	-5.9% to 0.2%	600	440	160	96
All providers	deepseek-4.1-flash	kimi-k3	exact_world	9.5%	4.0% to 14.7%	600	440	160	96
All providers	deepseek-4.1-flash	kimi-k3	task_success	9.5%	4.0% to 14.7%	600	440	160	96
All providers	deepseek-4.1-flash	kimi-k3	decision_correct	0.2%	0.0% to 0.7%	600	440	160	96
All providers	deepseek-4.1-flash	mimo-v2.6-flash	fact_f1	-0.1%	-2.7% to 2.3%	600	590	10	120
All providers	deepseek-4.1-flash	mimo-v2.6-flash	exact_world	7.6%	2.9% to 12.2%	600	590	10	120
All providers	deepseek-4.1-flash	mimo-v2.6-flash	task_success	9.3%	4.6% to 13.8%	600	590	10	120
All providers	deepseek-4.1-flash	mimo-v2.6-flash	decision_correct	10.2%	7.5% to 13.0%	600	590	10	120
All providers	deepseek-4.1-flash	mimo-v2.6-pro	fact_f1	2.8%	0.4% to 5.2%	600	595	5	120
All providers	deepseek-4.1-flash	mimo-v2.6-pro	exact_world	10.1%	6.2% to 14.0%	600	595	5	120
All providers	deepseek-4.1-flash	mimo-v2.6-pro	task_success	11.3%	7.2% to 15.3%	600	595	5	120
All providers	deepseek-4.1-flash	mimo-v2.6-pro	decision_correct	11.4%	8.7% to 14.3%	600	595	5	120
All providers	deepseek-4.1-flash	minimax-m3	fact_f1	11.1%	8.3% to 13.8%	600	595	5	120
All providers	deepseek-4.1-flash	minimax-m3	exact_world	15.0%	10.3% to 19.4%	600	595	5	120
All providers	deepseek-4.1-flash	minimax-m3	task_success	15.0%	10.3% to 19.4%	600	595	5	120
All providers	deepseek-4.1-flash	minimax-m3	decision_correct	3.4%	1.8% to 5.0%	600	595	5	120
All providers	deepseek-4.1-flash	qwen3.8-27b	fact_f1	-4.5%	-7.1% to -2.0%	600	595	5	120
All providers	deepseek-4.1-flash	qwen3.8-27b	exact_world	15.1%	10.4% to 19.9%	600	595	5	120
All providers	deepseek-4.1-flash	qwen3.8-27b	task_success	15.1%	10.4% to 19.9%	600	595	5	120
All providers	deepseek-4.1-flash	qwen3.8-27b	decision_correct	2.7%	1.2% to 4.4%	600	595	5	120
All providers	deepseek-v4-pro	gemini-3.6-flash	fact_f1	12.0%	9.4% to 14.8%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.6-flash	exact_world	-1.0%	-5.7% to 3.5%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.6-flash	task_success	-1.0%	-5.7% to 3.5%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.6-flash	decision_correct	-3.7%	-5.7% to -1.8%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.7-flash	fact_f1	0.2%	-1.8% to 2.2%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.7-flash	exact_world	-26.0%	-31.0% to -21.0%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.7-flash	task_success	-26.0%	-31.0% to -21.0%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.7-flash	decision_correct	-4.2%	-6.2% to -2.5%	600	600	0	120
All providers	deepseek-v4-pro	gemini-3.8-flash	fact_f1	5.0%	2.8% to 7.2%	600	598	2	120
All providers	deepseek-v4-pro	gemini-3.8-flash	exact_world	-16.4%	-21.3% to -11.7%	600	598	2	120
All providers	deepseek-v4-pro	gemini-3.8-flash	task_success	-16.4%	-21.3% to -11.7%	600	598	2	120
All providers	deepseek-v4-pro	gemini-3.8-flash	decision_correct	-4.3%	-6.2% to -2.7%	600	598	2	120
All providers	deepseek-v4-pro	glm-4.7-flash	fact_f1	24.5%	21.6% to 27.4%	600	566	34	120
All providers	deepseek-v4-pro	glm-4.7-flash	exact_world	22.6%	18.4% to 27.1%	600	566	34	120
All providers	deepseek-v4-pro	glm-4.7-flash	task_success	22.6%	18.4% to 27.1%	600	566	34	120
All providers	deepseek-v4-pro	glm-4.7-flash	decision_correct	13.1%	9.3% to 16.8%	600	566	34	120
All providers	deepseek-v4-pro	glm-5.3	fact_f1	6.4%	3.3% to 9.4%	600	564	36	120
All providers	deepseek-v4-pro	glm-5.3	exact_world	-13.5%	-18.2% to -9.0%	600	564	36	120
All providers	deepseek-v4-pro	glm-5.3	task_success	-13.3%	-18.0% to -8.8%	600	564	36	120
All providers	deepseek-v4-pro	glm-5.3	decision_correct	-1.2%	-3.6% to 1.1%	600	564	36	120
All providers	deepseek-v4-pro	glm-5.3-flash	fact_f1	24.3%	20.8% to 27.9%	600	596	4	120
All providers	deepseek-v4-pro	glm-5.3-flash	exact_world	16.6%	12.6% to 20.7%	600	596	4	120
All providers	deepseek-v4-pro	glm-5.3-flash	task_success	16.8%	12.8% to 20.8%	600	596	4	120
All providers	deepseek-v4-pro	glm-5.3-flash	decision_correct	-3.0%	-5.4% to -0.8%	600	596	4	120
All providers	deepseek-v4-pro	gpt-5.6-luna	fact_f1	10.1%	8.0% to 12.2%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-luna	exact_world	0.0%	-4.0% to 4.3%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-luna	task_success	1.0%	-3.2% to 5.3%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-luna	decision_correct	-1.8%	-4.2% to 0.3%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-sol	fact_f1	0.5%	-1.7% to 2.6%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-sol	exact_world	-25.8%	-31.3% to -20.2%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-sol	task_success	-25.8%	-31.3% to -20.2%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-sol	decision_correct	-4.7%	-6.7% to -2.8%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-terra	fact_f1	9.7%	7.4% to 12.0%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-terra	exact_world	-8.0%	-12.5% to -3.5%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-terra	task_success	-8.0%	-12.5% to -3.5%	600	600	0	120
All providers	deepseek-v4-pro	gpt-5.6-terra	decision_correct	-4.5%	-6.5% to -2.8%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-astra	fact_f1	-6.9%	-8.3% to -5.6%	600	550	50	115
All providers	deepseek-v4-pro	gpt-6-astra	exact_world	-43.5%	-48.7% to -37.9%	600	550	50	115
All providers	deepseek-v4-pro	gpt-6-astra	task_success	-43.5%	-48.7% to -37.9%	600	550	50	115
All providers	deepseek-v4-pro	gpt-6-astra	decision_correct	-4.4%	-6.3% to -2.7%	600	550	50	115
All providers	deepseek-v4-pro	gpt-6-luna	fact_f1	10.0%	7.5% to 12.5%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-luna	exact_world	0.2%	-4.5% to 4.8%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-luna	task_success	0.3%	-4.3% to 5.0%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-luna	decision_correct	-3.0%	-5.0% to -1.0%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-sol	fact_f1	-5.2%	-6.7% to -3.6%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-sol	exact_world	-31.7%	-36.8% to -26.3%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-sol	task_success	-31.5%	-36.7% to -26.2%	600	600	0	120
All providers	deepseek-v4-pro	gpt-6-sol	decision_correct	-3.2%	-5.2% to -1.3%	600	600	0	120
All providers	deepseek-v4-pro	grok-4.6	fact_f1	2.0%	0.3% to 3.5%	600	600	0	120
All providers	deepseek-v4-pro	grok-4.6	exact_world	5.7%	0.5% to 10.8%	600	600	0	120
All providers	deepseek-v4-pro	grok-4.6	task_success	5.7%	0.5% to 10.8%	600	600	0	120
All providers	deepseek-v4-pro	grok-4.6	decision_correct	-1.3%	-3.7% to 0.8%	600	600	0	120
All providers	deepseek-v4-pro	kimi-k2.6	fact_f1	0.9%	-0.6% to 2.5%	600	599	1	120
All providers	deepseek-v4-pro	kimi-k2.6	exact_world	6.0%	2.0% to 10.2%	600	599	1	120
All providers	deepseek-v4-pro	kimi-k2.6	task_success	6.0%	2.0% to 10.2%	600	599	1	120
All providers	deepseek-v4-pro	kimi-k2.6	decision_correct	-2.5%	-4.2% to -1.0%	600	599	1	120
All providers	deepseek-v4-pro	kimi-k3	fact_f1	6.9%	3.9% to 10.0%	600	443	157	96
All providers	deepseek-v4-pro	kimi-k3	exact_world	2.7%	-2.6% to 8.0%	600	443	157	96
All providers	deepseek-v4-pro	kimi-k3	task_success	2.7%	-2.6% to 8.0%	600	443	157	96
All providers	deepseek-v4-pro	kimi-k3	decision_correct	-4.3%	-6.5% to -2.3%	600	443	157	96
All providers	deepseek-v4-pro	mimo-v2.6-flash	fact_f1	12.1%	9.7% to 14.6%	600	594	6	120
All providers	deepseek-v4-pro	mimo-v2.6-flash	exact_world	1.9%	-2.2% to 6.0%	600	594	6	120
All providers	deepseek-v4-pro	mimo-v2.6-flash	task_success	3.5%	-0.5% to 7.8%	600	594	6	120
All providers	deepseek-v4-pro	mimo-v2.6-flash	decision_correct	5.4%	2.2% to 8.7%	600	594	6	120
All providers	deepseek-v4-pro	mimo-v2.6-pro	fact_f1	14.9%	12.3% to 17.6%	600	600	0	120
All providers	deepseek-v4-pro	mimo-v2.6-pro	exact_world	3.5%	-0.2% to 7.5%	600	600	0	120
All providers	deepseek-v4-pro	mimo-v2.6-pro	task_success	4.7%	0.7% to 9.0%	600	600	0	120
All providers	deepseek-v4-pro	mimo-v2.6-pro	decision_correct	6.8%	3.3% to 10.3%	600	600	0	120
All providers	deepseek-v4-pro	minimax-m3	fact_f1	23.0%	19.8% to 26.3%	600	600	0	120
All providers	deepseek-v4-pro	minimax-m3	exact_world	8.8%	5.0% to 12.7%	600	600	0	120
All providers	deepseek-v4-pro	minimax-m3	task_success	8.8%	5.0% to 12.7%	600	600	0	120
All providers	deepseek-v4-pro	minimax-m3	decision_correct	-1.3%	-3.5% to 0.7%	600	600	0	120
All providers	deepseek-v4-pro	qwen3.8-27b	fact_f1	7.8%	5.4% to 10.4%	600	600	0	120
All providers	deepseek-v4-pro	qwen3.8-27b	exact_world	9.0%	4.7% to 13.5%	600	600	0	120
All providers	deepseek-v4-pro	qwen3.8-27b	task_success	9.0%	4.7% to 13.5%	600	600	0	120
All providers	deepseek-v4-pro	qwen3.8-27b	decision_correct	-1.7%	-4.0% to 0.5%	600	600	0	120
All providers	gemini-3.6-flash	gemini-3.7-flash	fact_f1	-11.8%	-14.1% to -9.6%	600	600	0	120
All providers	gemini-3.6-flash	gemini-3.7-flash	exact_world	-25.0%	-29.8% to -20.2%	600	600	0	120
All providers	gemini-3.6-flash	gemini-3.7-flash	task_success	-25.0%	-29.8% to -20.2%	600	600	0	120
All providers	gemini-3.6-flash	gemini-3.7-flash	decision_correct	-0.5%	-1.2% to 0.0%	600	600	0	120
All providers	gemini-3.6-flash	gemini-3.8-flash	fact_f1	-7.0%	-9.0% to -5.1%	600	598	2	120
All providers	gemini-3.6-flash	gemini-3.8-flash	exact_world	-15.6%	-20.0% to -10.9%	600	598	2	120
All providers	gemini-3.6-flash	gemini-3.8-flash	task_success	-15.6%	-20.0% to -10.9%	600	598	2	120
All providers	gemini-3.6-flash	gemini-3.8-flash	decision_correct	-0.7%	-1.5% to 0.0%	600	598	2	120
All providers	gemini-3.6-flash	glm-4.7-flash	fact_f1	13.3%	10.2% to 16.4%	600	566	34	120
All providers	gemini-3.6-flash	glm-4.7-flash	exact_world	24.7%	20.7% to 29.0%	600	566	34	120
All providers	gemini-3.6-flash	glm-4.7-flash	task_success	24.7%	20.7% to 29.0%	600	566	34	120
All providers	gemini-3.6-flash	glm-4.7-flash	decision_correct	17.0%	13.6% to 20.3%	600	566	34	120
All providers	gemini-3.6-flash	glm-5.3	fact_f1	-5.3%	-8.3% to -2.3%	600	564	36	120
All providers	gemini-3.6-flash	glm-5.3	exact_world	-11.9%	-17.2% to -6.9%	600	564	36	120
All providers	gemini-3.6-flash	glm-5.3	task_success	-11.7%	-17.0% to -6.8%	600	564	36	120
All providers	gemini-3.6-flash	glm-5.3	decision_correct	2.7%	0.7% to 4.5%	600	564	36	120
All providers	gemini-3.6-flash	glm-5.3-flash	fact_f1	12.2%	10.0% to 14.5%	600	596	4	120
All providers	gemini-3.6-flash	glm-5.3-flash	exact_world	17.4%	13.1% to 22.0%	600	596	4	120
All providers	gemini-3.6-flash	glm-5.3-flash	task_success	17.6%	13.3% to 22.1%	600	596	4	120
All providers	gemini-3.6-flash	glm-5.3-flash	decision_correct	0.7%	-0.8% to 2.0%	600	596	4	120
All providers	gemini-3.6-flash	gpt-5.6-luna	fact_f1	-1.9%	-4.9% to 1.3%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-luna	exact_world	1.0%	-4.0% to 6.3%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-luna	task_success	2.0%	-3.0% to 7.2%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-luna	decision_correct	1.8%	0.3% to 3.2%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-sol	fact_f1	-11.5%	-14.1% to -8.9%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-sol	exact_world	-24.8%	-30.8% to -18.5%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-sol	task_success	-24.8%	-30.8% to -18.5%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-sol	decision_correct	-1.0%	-2.2% to -0.2%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-terra	fact_f1	-2.3%	-4.8% to 0.3%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-terra	exact_world	-7.0%	-12.0% to -2.0%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-terra	task_success	-7.0%	-12.0% to -2.0%	600	600	0	120
All providers	gemini-3.6-flash	gpt-5.6-terra	decision_correct	-0.8%	-1.7% to -0.2%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-astra	fact_f1	-17.1%	-19.8% to -14.3%	600	550	50	115
All providers	gemini-3.6-flash	gpt-6-astra	exact_world	-41.3%	-47.5% to -34.4%	600	550	50	115
All providers	gemini-3.6-flash	gpt-6-astra	task_success	-41.3%	-47.5% to -34.4%	600	550	50	115
All providers	gemini-3.6-flash	gpt-6-astra	decision_correct	-0.9%	-1.9% to -0.2%	600	550	50	115
All providers	gemini-3.6-flash	gpt-6-luna	fact_f1	-2.0%	-4.8% to 0.8%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-luna	exact_world	1.2%	-3.8% to 6.3%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-luna	task_success	1.3%	-3.7% to 6.5%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-luna	decision_correct	0.7%	-0.8% to 2.0%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-sol	fact_f1	-17.2%	-20.0% to -14.4%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-sol	exact_world	-30.7%	-36.7% to -24.2%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-sol	task_success	-30.5%	-36.5% to -24.0%	600	600	0	120
All providers	gemini-3.6-flash	gpt-6-sol	decision_correct	0.5%	-0.7% to 1.5%	600	600	0	120
All providers	gemini-3.6-flash	grok-4.6	fact_f1	-10.0%	-12.8% to -7.2%	600	600	0	120
All providers	gemini-3.6-flash	grok-4.6	exact_world	6.7%	1.2% to 12.2%	600	600	0	120
All providers	gemini-3.6-flash	grok-4.6	task_success	6.7%	1.2% to 12.2%	600	600	0	120
All providers	gemini-3.6-flash	grok-4.6	decision_correct	2.3%	1.0% to 4.0%	600	600	0	120
All providers	gemini-3.6-flash	kimi-k2.6	fact_f1	-11.1%	-13.7% to -8.6%	600	599	1	120
All providers	gemini-3.6-flash	kimi-k2.6	exact_world	7.0%	3.0% to 11.3%	600	599	1	120
All providers	gemini-3.6-flash	kimi-k2.6	task_success	7.0%	3.0% to 11.3%	600	599	1	120
All providers	gemini-3.6-flash	kimi-k2.6	decision_correct	1.2%	-0.3% to 2.8%	600	599	1	120
All providers	gemini-3.6-flash	kimi-k3	fact_f1	-1.1%	-3.6% to 1.2%	600	443	157	96
All providers	gemini-3.6-flash	kimi-k3	exact_world	5.0%	-0.2% to 10.2%	600	443	157	96
All providers	gemini-3.6-flash	kimi-k3	task_success	5.0%	-0.2% to 10.2%	600	443	157	96
All providers	gemini-3.6-flash	kimi-k3	decision_correct	-0.9%	-2.1% to 0.0%	600	443	157	96
All providers	gemini-3.6-flash	mimo-v2.6-flash	fact_f1	0.0%	-2.4% to 2.3%	600	594	6	120
All providers	gemini-3.6-flash	mimo-v2.6-flash	exact_world	2.7%	-1.3% to 6.7%	600	594	6	120
All providers	gemini-3.6-flash	mimo-v2.6-flash	task_success	4.4%	0.5% to 8.4%	600	594	6	120
All providers	gemini-3.6-flash	mimo-v2.6-flash	decision_correct	9.1%	6.4% to 12.1%	600	594	6	120
All providers	gemini-3.6-flash	mimo-v2.6-pro	fact_f1	2.9%	0.4% to 5.6%	600	600	0	120
All providers	gemini-3.6-flash	mimo-v2.6-pro	exact_world	4.5%	0.0% to 9.0%	600	600	0	120
All providers	gemini-3.6-flash	mimo-v2.6-pro	task_success	5.7%	1.3% to 10.3%	600	600	0	120
All providers	gemini-3.6-flash	mimo-v2.6-pro	decision_correct	10.5%	7.5% to 13.7%	600	600	0	120
All providers	gemini-3.6-flash	minimax-m3	fact_f1	11.0%	7.9% to 14.2%	600	600	0	120
All providers	gemini-3.6-flash	minimax-m3	exact_world	9.8%	5.0% to 14.7%	600	600	0	120
All providers	gemini-3.6-flash	minimax-m3	task_success	9.8%	5.0% to 14.7%	600	600	0	120
All providers	gemini-3.6-flash	minimax-m3	decision_correct	2.3%	0.8% to 3.8%	600	600	0	120
All providers	gemini-3.6-flash	qwen3.8-27b	fact_f1	-4.1%	-6.6% to -1.7%	600	600	0	120
All providers	gemini-3.6-flash	qwen3.8-27b	exact_world	10.0%	5.7% to 14.3%	600	600	0	120
All providers	gemini-3.6-flash	qwen3.8-27b	task_success	10.0%	5.7% to 14.3%	600	600	0	120
All providers	gemini-3.6-flash	qwen3.8-27b	decision_correct	2.0%	0.7% to 3.7%	600	600	0	120
All providers	gemini-3.7-flash	gemini-3.8-flash	fact_f1	4.8%	3.3% to 6.4%	600	598	2	120
All providers	gemini-3.7-flash	gemini-3.8-flash	exact_world	9.7%	5.7% to 13.5%	600	598	2	120
All providers	gemini-3.7-flash	gemini-3.8-flash	task_success	9.7%	5.7% to 13.5%	600	598	2	120
All providers	gemini-3.7-flash	gemini-3.8-flash	decision_correct	-0.2%	-0.5% to 0.0%	600	598	2	120
All providers	gemini-3.7-flash	glm-4.7-flash	fact_f1	24.9%	22.3% to 27.6%	600	566	34	120
All providers	gemini-3.7-flash	glm-4.7-flash	exact_world	49.5%	45.1% to 53.9%	600	566	34	120
All providers	gemini-3.7-flash	glm-4.7-flash	task_success	49.5%	45.1% to 53.9%	600	566	34	120
All providers	gemini-3.7-flash	glm-4.7-flash	decision_correct	17.3%	14.0% to 20.6%	600	566	34	120
All providers	gemini-3.7-flash	glm-5.3	fact_f1	6.1%	3.4% to 8.9%	600	564	36	120
All providers	gemini-3.7-flash	glm-5.3	exact_world	11.7%	6.0% to 16.9%	600	564	36	120
All providers	gemini-3.7-flash	glm-5.3	task_success	11.9%	6.2% to 17.1%	600	564	36	120
All providers	gemini-3.7-flash	glm-5.3	decision_correct	3.2%	1.6% to 5.0%	600	564	36	120
All providers	gemini-3.7-flash	glm-5.3-flash	fact_f1	24.1%	21.2% to 27.1%	600	596	4	120
All providers	gemini-3.7-flash	glm-5.3-flash	exact_world	42.6%	38.3% to 47.2%	600	596	4	120
All providers	gemini-3.7-flash	glm-5.3-flash	task_success	42.8%	38.4% to 47.3%	600	596	4	120
All providers	gemini-3.7-flash	glm-5.3-flash	decision_correct	1.2%	-0.2% to 2.5%	600	596	4	120
All providers	gemini-3.7-flash	gpt-5.6-luna	fact_f1	9.9%	7.4% to 12.6%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-luna	exact_world	26.0%	20.8% to 31.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-luna	task_success	27.0%	21.8% to 32.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-luna	decision_correct	2.3%	1.2% to 3.7%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-sol	fact_f1	0.3%	-1.7% to 2.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-sol	exact_world	0.2%	-5.7% to 6.5%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-sol	task_success	0.2%	-5.7% to 6.5%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-sol	decision_correct	-0.5%	-1.3% to 0.0%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-terra	fact_f1	9.6%	7.5% to 11.8%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-terra	exact_world	18.0%	13.3% to 22.7%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-terra	task_success	18.0%	13.3% to 22.7%	600	600	0	120
All providers	gemini-3.7-flash	gpt-5.6-terra	decision_correct	-0.3%	-0.8% to 0.0%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-astra	fact_f1	-6.6%	-8.3% to -4.8%	600	550	50	115
All providers	gemini-3.7-flash	gpt-6-astra	exact_world	-18.0%	-23.7% to -12.0%	600	550	50	115
All providers	gemini-3.7-flash	gpt-6-astra	task_success	-18.0%	-23.7% to -12.0%	600	550	50	115
All providers	gemini-3.7-flash	gpt-6-astra	decision_correct	-0.4%	-0.9% to 0.0%	600	550	50	115
All providers	gemini-3.7-flash	gpt-6-luna	fact_f1	9.8%	7.5% to 12.2%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-luna	exact_world	26.2%	21.2% to 31.2%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-luna	task_success	26.3%	21.3% to 31.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-luna	decision_correct	1.2%	0.0% to 2.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-sol	fact_f1	-5.3%	-7.3% to -3.3%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-sol	exact_world	-5.7%	-11.5% to 0.0%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-sol	task_success	-5.5%	-11.3% to 0.2%	600	600	0	120
All providers	gemini-3.7-flash	gpt-6-sol	decision_correct	1.0%	0.2% to 2.0%	600	600	0	120
All providers	gemini-3.7-flash	grok-4.6	fact_f1	1.8%	0.0% to 3.7%	600	600	0	120
All providers	gemini-3.7-flash	grok-4.6	exact_world	31.7%	27.0% to 36.3%	600	600	0	120
All providers	gemini-3.7-flash	grok-4.6	task_success	31.7%	27.0% to 36.3%	600	600	0	120
All providers	gemini-3.7-flash	grok-4.6	decision_correct	2.8%	1.2% to 4.7%	600	600	0	120
All providers	gemini-3.7-flash	kimi-k2.6	fact_f1	0.7%	-1.1% to 2.6%	600	599	1	120
All providers	gemini-3.7-flash	kimi-k2.6	exact_world	32.1%	27.7% to 36.6%	600	599	1	120
All providers	gemini-3.7-flash	kimi-k2.6	task_success	32.1%	27.7% to 36.6%	600	599	1	120
All providers	gemini-3.7-flash	kimi-k2.6	decision_correct	1.7%	0.3% to 3.2%	600	599	1	120
All providers	gemini-3.7-flash	kimi-k3	fact_f1	8.3%	5.9% to 10.7%	600	443	157	96
All providers	gemini-3.7-flash	kimi-k3	exact_world	29.1%	23.7% to 34.5%	600	443	157	96
All providers	gemini-3.7-flash	kimi-k3	task_success	29.1%	23.7% to 34.5%	600	443	157	96
All providers	gemini-3.7-flash	kimi-k3	decision_correct	-0.5%	-1.1% to 0.0%	600	443	157	96
All providers	gemini-3.7-flash	mimo-v2.6-flash	fact_f1	11.9%	9.8% to 14.0%	600	594	6	120
All providers	gemini-3.7-flash	mimo-v2.6-flash	exact_world	27.6%	22.7% to 32.5%	600	594	6	120
All providers	gemini-3.7-flash	mimo-v2.6-flash	task_success	29.3%	24.6% to 34.0%	600	594	6	120
All providers	gemini-3.7-flash	mimo-v2.6-flash	decision_correct	9.6%	7.0% to 12.5%	600	594	6	120
All providers	gemini-3.7-flash	mimo-v2.6-pro	fact_f1	14.7%	12.4% to 17.1%	600	600	0	120
All providers	gemini-3.7-flash	mimo-v2.6-pro	exact_world	29.5%	24.8% to 34.5%	600	600	0	120
All providers	gemini-3.7-flash	mimo-v2.6-pro	task_success	30.7%	25.8% to 35.8%	600	600	0	120
All providers	gemini-3.7-flash	mimo-v2.6-pro	decision_correct	11.0%	8.0% to 14.0%	600	600	0	120
All providers	gemini-3.7-flash	minimax-m3	fact_f1	22.9%	19.9% to 25.8%	600	600	0	120
All providers	gemini-3.7-flash	minimax-m3	exact_world	34.8%	30.7% to 39.2%	600	600	0	120
All providers	gemini-3.7-flash	minimax-m3	task_success	34.8%	30.7% to 39.2%	600	600	0	120
All providers	gemini-3.7-flash	minimax-m3	decision_correct	2.8%	1.5% to 4.3%	600	600	0	120
All providers	gemini-3.7-flash	qwen3.8-27b	fact_f1	7.7%	5.8% to 9.7%	600	600	0	120
All providers	gemini-3.7-flash	qwen3.8-27b	exact_world	35.0%	30.7% to 39.3%	600	600	0	120
All providers	gemini-3.7-flash	qwen3.8-27b	task_success	35.0%	30.7% to 39.3%	600	600	0	120
All providers	gemini-3.7-flash	qwen3.8-27b	decision_correct	2.5%	1.2% to 4.0%	600	600	0	120
All providers	gemini-3.8-flash	glm-4.7-flash	fact_f1	20.5%	17.7% to 23.5%	600	564	36	120
All providers	gemini-3.8-flash	glm-4.7-flash	exact_world	40.2%	35.6% to 45.1%	600	564	36	120
All providers	gemini-3.8-flash	glm-4.7-flash	task_success	40.2%	35.6% to 45.1%	600	564	36	120
All providers	gemini-3.8-flash	glm-4.7-flash	decision_correct	17.4%	14.1% to 20.7%	600	564	36	120
All providers	gemini-3.8-flash	glm-5.3	fact_f1	1.3%	-1.4% to 3.9%	600	562	38	120
All providers	gemini-3.8-flash	glm-5.3	exact_world	2.7%	-3.0% to 8.3%	600	562	38	120
All providers	gemini-3.8-flash	glm-5.3	task_success	2.8%	-2.9% to 8.6%	600	562	38	120
All providers	gemini-3.8-flash	glm-5.3	decision_correct	3.4%	1.8% to 5.0%	600	562	38	120
All providers	gemini-3.8-flash	glm-5.3-flash	fact_f1	19.2%	16.7% to 21.8%	600	594	6	120
All providers	gemini-3.8-flash	glm-5.3-flash	exact_world	33.0%	28.3% to 37.8%	600	594	6	120
All providers	gemini-3.8-flash	glm-5.3-flash	task_success	33.2%	28.6% to 37.9%	600	594	6	120
All providers	gemini-3.8-flash	glm-5.3-flash	decision_correct	1.3%	0.3% to 2.5%	600	594	6	120
All providers	gemini-3.8-flash	gpt-5.6-luna	fact_f1	5.1%	2.7% to 7.6%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-luna	exact_world	16.6%	11.4% to 21.9%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-luna	task_success	17.6%	12.5% to 22.9%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-luna	decision_correct	2.5%	1.3% to 3.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-sol	fact_f1	-4.6%	-6.5% to -2.5%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-sol	exact_world	-9.4%	-15.2% to -2.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-sol	task_success	-9.4%	-15.2% to -2.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-sol	decision_correct	-0.3%	-0.8% to 0.0%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-terra	fact_f1	4.7%	2.5% to 6.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-terra	exact_world	8.5%	3.7% to 13.4%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-terra	task_success	8.5%	3.7% to 13.4%	600	598	2	120
All providers	gemini-3.8-flash	gpt-5.6-terra	decision_correct	-0.2%	-0.5% to 0.0%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-astra	fact_f1	-11.2%	-13.3% to -9.0%	600	548	52	115
All providers	gemini-3.8-flash	gpt-6-astra	exact_world	-26.5%	-32.2% to -20.6%	600	548	52	115
All providers	gemini-3.8-flash	gpt-6-astra	task_success	-26.5%	-32.2% to -20.6%	600	548	52	115
All providers	gemini-3.8-flash	gpt-6-astra	decision_correct	-0.4%	-0.9% to 0.0%	600	548	52	115
All providers	gemini-3.8-flash	gpt-6-luna	fact_f1	5.0%	2.6% to 7.3%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-luna	exact_world	16.6%	11.5% to 21.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-luna	task_success	16.7%	11.7% to 21.9%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-luna	decision_correct	1.3%	0.3% to 2.3%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-sol	fact_f1	-10.1%	-12.4% to -7.8%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-sol	exact_world	-15.2%	-21.0% to -9.4%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-sol	task_success	-15.1%	-20.7% to -9.2%	600	598	2	120
All providers	gemini-3.8-flash	gpt-6-sol	decision_correct	1.2%	0.3% to 2.2%	600	598	2	120
All providers	gemini-3.8-flash	grok-4.6	fact_f1	-2.9%	-5.2% to -0.7%	600	598	2	120
All providers	gemini-3.8-flash	grok-4.6	exact_world	22.1%	16.7% to 27.4%	600	598	2	120
All providers	gemini-3.8-flash	grok-4.6	task_success	22.1%	16.7% to 27.4%	600	598	2	120
All providers	gemini-3.8-flash	grok-4.6	decision_correct	3.0%	1.3% to 5.0%	600	598	2	120
All providers	gemini-3.8-flash	kimi-k2.6	fact_f1	-4.1%	-6.1% to -2.1%	600	597	3	120
All providers	gemini-3.8-flash	kimi-k2.6	exact_world	22.6%	18.2% to 27.1%	600	597	3	120
All providers	gemini-3.8-flash	kimi-k2.6	task_success	22.6%	18.2% to 27.1%	600	597	3	120
All providers	gemini-3.8-flash	kimi-k2.6	decision_correct	1.8%	0.7% to 3.3%	600	597	3	120
All providers	gemini-3.8-flash	kimi-k3	fact_f1	4.3%	2.2% to 6.7%	600	441	159	96
All providers	gemini-3.8-flash	kimi-k3	exact_world	19.7%	14.3% to 25.1%	600	441	159	96
All providers	gemini-3.8-flash	kimi-k3	task_success	19.7%	14.3% to 25.1%	600	441	159	96
All providers	gemini-3.8-flash	kimi-k3	decision_correct	-0.2%	-0.7% to 0.0%	600	441	159	96
All providers	gemini-3.8-flash	mimo-v2.6-flash	fact_f1	7.0%	5.2% to 8.8%	600	592	8	120
All providers	gemini-3.8-flash	mimo-v2.6-flash	exact_world	18.2%	13.8% to 22.7%	600	592	8	120
All providers	gemini-3.8-flash	mimo-v2.6-flash	task_success	19.9%	15.5% to 24.4%	600	592	8	120
All providers	gemini-3.8-flash	mimo-v2.6-flash	decision_correct	9.8%	7.2% to 12.6%	600	592	8	120
All providers	gemini-3.8-flash	mimo-v2.6-pro	fact_f1	10.0%	7.6% to 12.4%	600	598	2	120
All providers	gemini-3.8-flash	mimo-v2.6-pro	exact_world	20.2%	15.7% to 24.9%	600	598	2	120
All providers	gemini-3.8-flash	mimo-v2.6-pro	task_success	21.4%	16.8% to 26.1%	600	598	2	120
All providers	gemini-3.8-flash	mimo-v2.6-pro	decision_correct	11.2%	8.4% to 14.2%	600	598	2	120
All providers	gemini-3.8-flash	minimax-m3	fact_f1	18.1%	15.3% to 20.9%	600	598	2	120
All providers	gemini-3.8-flash	minimax-m3	exact_world	25.4%	21.2% to 29.9%	600	598	2	120
All providers	gemini-3.8-flash	minimax-m3	task_success	25.4%	21.2% to 29.9%	600	598	2	120
All providers	gemini-3.8-flash	minimax-m3	decision_correct	3.0%	1.7% to 4.5%	600	598	2	120
All providers	gemini-3.8-flash	qwen3.8-27b	fact_f1	2.9%	1.0% to 5.0%	600	598	2	120
All providers	gemini-3.8-flash	qwen3.8-27b	exact_world	25.4%	20.7% to 30.4%	600	598	2	120
All providers	gemini-3.8-flash	qwen3.8-27b	task_success	25.4%	20.7% to 30.4%	600	598	2	120
All providers	gemini-3.8-flash	qwen3.8-27b	decision_correct	2.7%	1.3% to 4.3%	600	598	2	120
All providers	glm-4.7-flash	glm-5.3	fact_f1	-17.8%	-20.9% to -14.4%	600	531	69	120
All providers	glm-4.7-flash	glm-5.3	exact_world	-36.0%	-40.5% to -31.6%	600	531	69	120
All providers	glm-4.7-flash	glm-5.3	task_success	-35.8%	-40.3% to -31.4%	600	531	69	120
All providers	glm-4.7-flash	glm-5.3	decision_correct	-13.4%	-17.3% to -9.4%	600	531	69	120
All providers	glm-4.7-flash	glm-5.3-flash	fact_f1	-0.5%	-4.1% to 2.9%	600	562	38	120
All providers	glm-4.7-flash	glm-5.3-flash	exact_world	-6.8%	-10.1% to -3.6%	600	562	38	120
All providers	glm-4.7-flash	glm-5.3-flash	task_success	-6.6%	-9.9% to -3.4%	600	562	38	120
All providers	glm-4.7-flash	glm-5.3-flash	decision_correct	-15.7%	-19.1% to -12.1%	600	562	38	120
All providers	glm-4.7-flash	gpt-5.6-luna	fact_f1	-14.3%	-17.6% to -10.9%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-luna	exact_world	-23.3%	-27.3% to -19.4%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-luna	task_success	-22.3%	-26.2% to -18.4%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-luna	decision_correct	-15.2%	-18.7% to -11.9%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-sol	fact_f1	-24.1%	-27.2% to -21.1%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-sol	exact_world	-47.9%	-52.8% to -42.6%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-sol	task_success	-47.9%	-52.8% to -42.6%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-sol	decision_correct	-17.5%	-20.9% to -14.2%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-terra	fact_f1	-15.1%	-18.4% to -11.9%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-terra	exact_world	-31.6%	-36.1% to -27.3%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-terra	task_success	-31.6%	-36.1% to -27.3%	600	566	34	120
All providers	glm-4.7-flash	gpt-5.6-terra	decision_correct	-17.5%	-20.9% to -14.2%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-astra	fact_f1	-30.2%	-33.0% to -27.4%	600	520	80	115
All providers	glm-4.7-flash	gpt-6-astra	exact_world	-65.6%	-70.4% to -60.3%	600	520	80	115
All providers	glm-4.7-flash	gpt-6-astra	task_success	-65.6%	-70.4% to -60.3%	600	520	80	115
All providers	glm-4.7-flash	gpt-6-astra	decision_correct	-17.9%	-21.6% to -14.5%	600	520	80	115
All providers	glm-4.7-flash	gpt-6-luna	fact_f1	-15.2%	-18.5% to -11.9%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-luna	exact_world	-23.1%	-27.2% to -19.2%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-luna	task_success	-23.0%	-27.0% to -19.2%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-luna	decision_correct	-15.9%	-19.4% to -12.5%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-sol	fact_f1	-29.5%	-32.4% to -26.5%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-sol	exact_world	-53.5%	-58.6% to -48.3%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-sol	task_success	-53.5%	-58.6% to -48.3%	600	566	34	120
All providers	glm-4.7-flash	gpt-6-sol	decision_correct	-16.3%	-19.5% to -13.0%	600	566	34	120
All providers	glm-4.7-flash	grok-4.6	fact_f1	-22.6%	-25.4% to -19.7%	600	566	34	120
All providers	glm-4.7-flash	grok-4.6	exact_world	-17.5%	-22.1% to -13.0%	600	566	34	120
All providers	glm-4.7-flash	grok-4.6	task_success	-17.5%	-22.1% to -13.0%	600	566	34	120
All providers	glm-4.7-flash	grok-4.6	decision_correct	-14.5%	-18.0% to -10.7%	600	566	34	120
All providers	glm-4.7-flash	kimi-k2.6	fact_f1	-23.8%	-26.6% to -20.9%	600	565	35	120
All providers	glm-4.7-flash	kimi-k2.6	exact_world	-17.2%	-21.1% to -13.4%	600	565	35	120
All providers	glm-4.7-flash	kimi-k2.6	task_success	-17.2%	-21.1% to -13.4%	600	565	35	120
All providers	glm-4.7-flash	kimi-k2.6	decision_correct	-15.4%	-18.9% to -12.1%	600	565	35	120
All providers	glm-4.7-flash	kimi-k3	fact_f1	-16.0%	-20.3% to -12.0%	600	417	183	96
All providers	glm-4.7-flash	kimi-k3	exact_world	-21.6%	-26.5% to -16.5%	600	417	183	96
All providers	glm-4.7-flash	kimi-k3	task_success	-21.6%	-26.5% to -16.5%	600	417	183	96
All providers	glm-4.7-flash	kimi-k3	decision_correct	-18.0%	-22.2% to -14.0%	600	417	183	96
All providers	glm-4.7-flash	mimo-v2.6-flash	fact_f1	-12.9%	-16.0% to -9.8%	600	561	39	120
All providers	glm-4.7-flash	mimo-v2.6-flash	exact_world	-21.2%	-25.4% to -17.5%	600	561	39	120
All providers	glm-4.7-flash	mimo-v2.6-flash	task_success	-19.4%	-23.5% to -15.8%	600	561	39	120
All providers	glm-4.7-flash	mimo-v2.6-flash	decision_correct	-8.4%	-12.4% to -4.5%	600	561	39	120
All providers	glm-4.7-flash	mimo-v2.6-pro	fact_f1	-10.0%	-13.3% to -6.8%	600	566	34	120
All providers	glm-4.7-flash	mimo-v2.6-pro	exact_world	-19.6%	-23.7% to -15.7%	600	566	34	120
All providers	glm-4.7-flash	mimo-v2.6-pro	task_success	-18.4%	-22.6% to -14.2%	600	566	34	120
All providers	glm-4.7-flash	mimo-v2.6-pro	decision_correct	-6.4%	-11.1% to -1.7%	600	566	34	120
All providers	glm-4.7-flash	minimax-m3	fact_f1	-2.2%	-6.1% to 1.5%	600	566	34	120
All providers	glm-4.7-flash	minimax-m3	exact_world	-14.3%	-18.1% to -10.6%	600	566	34	120
All providers	glm-4.7-flash	minimax-m3	task_success	-14.3%	-18.1% to -10.6%	600	566	34	120
All providers	glm-4.7-flash	minimax-m3	decision_correct	-14.8%	-18.3% to -11.4%	600	566	34	120
All providers	glm-4.7-flash	qwen3.8-27b	fact_f1	-16.8%	-19.6% to -13.9%	600	566	34	120
All providers	glm-4.7-flash	qwen3.8-27b	exact_world	-14.1%	-18.3% to -10.2%	600	566	34	120
All providers	glm-4.7-flash	qwen3.8-27b	task_success	-14.1%	-18.3% to -10.2%	600	566	34	120
All providers	glm-4.7-flash	qwen3.8-27b	decision_correct	-15.0%	-18.5% to -11.5%	600	566	34	120
All providers	glm-5.3	glm-5.3-flash	fact_f1	17.3%	14.4% to 20.3%	600	560	40	120
All providers	glm-5.3	glm-5.3-flash	exact_world	29.1%	24.6% to 34.2%	600	560	40	120
All providers	glm-5.3	glm-5.3-flash	task_success	29.1%	24.6% to 34.1%	600	560	40	120
All providers	glm-5.3	glm-5.3-flash	decision_correct	-2.0%	-4.1% to 0.0%	600	560	40	120
All providers	glm-5.3	gpt-5.6-luna	fact_f1	3.5%	0.3% to 7.0%	600	564	36	120
All providers	glm-5.3	gpt-5.6-luna	exact_world	13.1%	7.8% to 18.5%	600	564	36	120
All providers	glm-5.3	gpt-5.6-luna	task_success	14.0%	8.8% to 19.4%	600	564	36	120
All providers	glm-5.3	gpt-5.6-luna	decision_correct	-0.7%	-2.7% to 1.2%	600	564	36	120
All providers	glm-5.3	gpt-5.6-sol	fact_f1	-5.9%	-8.7% to -3.2%	600	564	36	120
All providers	glm-5.3	gpt-5.6-sol	exact_world	-11.7%	-17.4% to -5.2%	600	564	36	120
All providers	glm-5.3	gpt-5.6-sol	task_success	-11.9%	-17.6% to -5.3%	600	564	36	120
All providers	glm-5.3	gpt-5.6-sol	decision_correct	-3.7%	-5.4% to -2.3%	600	564	36	120
All providers	glm-5.3	gpt-5.6-terra	fact_f1	3.4%	0.3% to 6.4%	600	564	36	120
All providers	glm-5.3	gpt-5.6-terra	exact_world	5.3%	0.4% to 10.5%	600	564	36	120
All providers	glm-5.3	gpt-5.6-terra	task_success	5.1%	0.2% to 10.4%	600	564	36	120
All providers	glm-5.3	gpt-5.6-terra	decision_correct	-3.5%	-5.2% to -2.0%	600	564	36	120
All providers	glm-5.3	gpt-6-astra	fact_f1	-12.0%	-15.0% to -9.0%	600	517	83	115
All providers	glm-5.3	gpt-6-astra	exact_world	-28.8%	-35.1% to -21.9%	600	517	83	115
All providers	glm-5.3	gpt-6-astra	task_success	-29.0%	-35.3% to -22.1%	600	517	83	115
All providers	glm-5.3	gpt-6-astra	decision_correct	-3.7%	-5.4% to -2.1%	600	517	83	115
All providers	glm-5.3	gpt-6-luna	fact_f1	3.5%	0.1% to 6.7%	600	564	36	120
All providers	glm-5.3	gpt-6-luna	exact_world	14.0%	8.7% to 19.5%	600	564	36	120
All providers	glm-5.3	gpt-6-luna	task_success	14.0%	8.7% to 19.7%	600	564	36	120
All providers	glm-5.3	gpt-6-luna	decision_correct	-2.3%	-4.0% to -0.7%	600	564	36	120
All providers	glm-5.3	gpt-6-sol	fact_f1	-11.5%	-14.6% to -8.5%	600	564	36	120
All providers	glm-5.3	gpt-6-sol	exact_world	-18.4%	-24.0% to -12.5%	600	564	36	120
All providers	glm-5.3	gpt-6-sol	task_success	-18.4%	-23.9% to -12.5%	600	564	36	120
All providers	glm-5.3	gpt-6-sol	decision_correct	-2.3%	-4.0% to -0.7%	600	564	36	120
All providers	glm-5.3	grok-4.6	fact_f1	-4.4%	-7.5% to -1.5%	600	564	36	120
All providers	glm-5.3	grok-4.6	exact_world	18.8%	12.9% to 24.9%	600	564	36	120
All providers	glm-5.3	grok-4.6	task_success	18.6%	12.8% to 24.6%	600	564	36	120
All providers	glm-5.3	grok-4.6	decision_correct	-0.4%	-2.7% to 2.1%	600	564	36	120
All providers	glm-5.3	kimi-k2.6	fact_f1	-5.5%	-8.3% to -2.8%	600	563	37	120
All providers	glm-5.3	kimi-k2.6	exact_world	18.7%	13.4% to 24.2%	600	563	37	120
All providers	glm-5.3	kimi-k2.6	task_success	18.5%	13.1% to 24.1%	600	563	37	120
All providers	glm-5.3	kimi-k2.6	decision_correct	-1.6%	-3.6% to 0.2%	600	563	37	120
All providers	glm-5.3	kimi-k3	fact_f1	4.0%	1.6% to 6.7%	600	419	181	94
All providers	glm-5.3	kimi-k3	exact_world	17.2%	12.0% to 23.0%	600	419	181	94
All providers	glm-5.3	kimi-k3	task_success	16.9%	11.7% to 22.7%	600	419	181	94
All providers	glm-5.3	kimi-k3	decision_correct	-3.3%	-5.4% to -1.7%	600	419	181	94
All providers	glm-5.3	mimo-v2.6-flash	fact_f1	5.8%	2.7% to 8.9%	600	559	41	120
All providers	glm-5.3	mimo-v2.6-flash	exact_world	15.0%	10.1% to 20.0%	600	559	41	120
All providers	glm-5.3	mimo-v2.6-flash	task_success	16.6%	11.7% to 21.6%	600	559	41	120
All providers	glm-5.3	mimo-v2.6-flash	decision_correct	6.4%	3.5% to 9.6%	600	559	41	120
All providers	glm-5.3	mimo-v2.6-pro	fact_f1	7.9%	5.1% to 10.9%	600	564	36	120
All providers	glm-5.3	mimo-v2.6-pro	exact_world	16.3%	11.7% to 21.5%	600	564	36	120
All providers	glm-5.3	mimo-v2.6-pro	task_success	17.0%	12.2% to 22.3%	600	564	36	120
All providers	glm-5.3	mimo-v2.6-pro	decision_correct	7.4%	4.4% to 10.6%	600	564	36	120
All providers	glm-5.3	minimax-m3	fact_f1	16.6%	12.9% to 20.6%	600	564	36	120
All providers	glm-5.3	minimax-m3	exact_world	22.7%	18.1% to 27.7%	600	564	36	120
All providers	glm-5.3	minimax-m3	task_success	22.5%	17.9% to 27.5%	600	564	36	120
All providers	glm-5.3	minimax-m3	decision_correct	-0.5%	-2.5% to 1.4%	600	564	36	120
All providers	glm-5.3	qwen3.8-27b	fact_f1	1.2%	-1.9% to 4.3%	600	564	36	120
All providers	glm-5.3	qwen3.8-27b	exact_world	21.5%	16.6% to 26.6%	600	564	36	120
All providers	glm-5.3	qwen3.8-27b	task_success	21.3%	16.4% to 26.5%	600	564	36	120
All providers	glm-5.3	qwen3.8-27b	decision_correct	-0.5%	-2.9% to 1.9%	600	564	36	120
All providers	glm-5.3-flash	gpt-5.6-luna	fact_f1	-14.2%	-17.6% to -10.4%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-luna	exact_world	-16.6%	-20.9% to -12.4%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-luna	task_success	-15.8%	-20.1% to -11.5%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-luna	decision_correct	1.2%	-0.5% to 2.9%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-sol	fact_f1	-23.9%	-27.0% to -20.9%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-sol	exact_world	-42.6%	-47.8% to -37.4%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-sol	task_success	-42.8%	-48.0% to -37.6%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-sol	decision_correct	-1.7%	-2.7% to -0.8%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-terra	fact_f1	-14.5%	-17.7% to -11.5%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-terra	exact_world	-24.3%	-28.7% to -19.9%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-terra	task_success	-24.5%	-28.9% to -20.1%	600	596	4	120
All providers	glm-5.3-flash	gpt-5.6-terra	decision_correct	-1.5%	-2.7% to -0.5%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-astra	fact_f1	-29.3%	-32.7% to -25.8%	600	546	54	115
All providers	glm-5.3-flash	gpt-6-astra	exact_world	-60.3%	-65.2% to -55.0%	600	546	54	115
All providers	glm-5.3-flash	gpt-6-astra	task_success	-60.3%	-65.2% to -55.0%	600	546	54	115
All providers	glm-5.3-flash	gpt-6-astra	decision_correct	-1.6%	-2.8% to -0.7%	600	546	54	115
All providers	glm-5.3-flash	gpt-6-luna	fact_f1	-14.2%	-17.5% to -10.9%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-luna	exact_world	-16.4%	-20.8% to -12.4%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-luna	task_success	-16.4%	-20.6% to -12.4%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-luna	decision_correct	0.0%	-1.3% to 1.3%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-sol	fact_f1	-29.5%	-33.0% to -25.9%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-sol	exact_world	-48.3%	-53.4% to -43.0%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-sol	task_success	-48.3%	-53.4% to -43.0%	600	596	4	120
All providers	glm-5.3-flash	gpt-6-sol	decision_correct	-0.2%	-1.7% to 1.3%	600	596	4	120
All providers	glm-5.3-flash	grok-4.6	fact_f1	-22.3%	-25.7% to -19.0%	600	596	4	120
All providers	glm-5.3-flash	grok-4.6	exact_world	-10.9%	-15.5% to -6.7%	600	596	4	120
All providers	glm-5.3-flash	grok-4.6	task_success	-11.1%	-15.7% to -6.9%	600	596	4	120
All providers	glm-5.3-flash	grok-4.6	decision_correct	1.7%	-0.7% to 4.2%	600	596	4	120
All providers	glm-5.3-flash	kimi-k2.6	fact_f1	-23.3%	-26.5% to -20.2%	600	595	5	120
All providers	glm-5.3-flash	kimi-k2.6	exact_world	-10.6%	-14.8% to -6.4%	600	595	5	120
All providers	glm-5.3-flash	kimi-k2.6	task_success	-10.8%	-15.0% to -6.5%	600	595	5	120
All providers	glm-5.3-flash	kimi-k2.6	decision_correct	0.5%	-1.2% to 2.2%	600	595	5	120
All providers	glm-5.3-flash	kimi-k3	fact_f1	-11.5%	-14.5% to -8.6%	600	439	161	96
All providers	glm-5.3-flash	kimi-k3	exact_world	-13.7%	-18.0% to -9.2%	600	439	161	96
All providers	glm-5.3-flash	kimi-k3	task_success	-13.7%	-18.0% to -9.2%	600	439	161	96
All providers	glm-5.3-flash	kimi-k3	decision_correct	-1.1%	-2.4% to 0.0%	600	439	161	96
All providers	glm-5.3-flash	mimo-v2.6-flash	fact_f1	-12.3%	-15.2% to -9.5%	600	590	10	120
All providers	glm-5.3-flash	mimo-v2.6-flash	exact_world	-15.1%	-18.8% to -11.7%	600	590	10	120
All providers	glm-5.3-flash	mimo-v2.6-flash	task_success	-13.6%	-17.2% to -10.3%	600	590	10	120
All providers	glm-5.3-flash	mimo-v2.6-flash	decision_correct	8.3%	5.6% to 11.2%	600	590	10	120
All providers	glm-5.3-flash	mimo-v2.6-pro	fact_f1	-9.3%	-11.8% to -6.8%	600	596	4	120
All providers	glm-5.3-flash	mimo-v2.6-pro	exact_world	-12.8%	-16.1% to -9.4%	600	596	4	120
All providers	glm-5.3-flash	mimo-v2.6-pro	task_success	-11.7%	-15.2% to -8.1%	600	596	4	120
All providers	glm-5.3-flash	mimo-v2.6-pro	decision_correct	9.9%	7.0% to 13.1%	600	596	4	120
All providers	glm-5.3-flash	minimax-m3	fact_f1	-1.2%	-4.3% to 2.1%	600	596	4	120
All providers	glm-5.3-flash	minimax-m3	exact_world	-7.9%	-11.4% to -4.4%	600	596	4	120
All providers	glm-5.3-flash	minimax-m3	task_success	-8.1%	-11.7% to -4.5%	600	596	4	120
All providers	glm-5.3-flash	minimax-m3	decision_correct	1.7%	-0.2% to 3.7%	600	596	4	120
All providers	glm-5.3-flash	qwen3.8-27b	fact_f1	-16.5%	-19.5% to -13.4%	600	596	4	120
All providers	glm-5.3-flash	qwen3.8-27b	exact_world	-7.7%	-11.6% to -4.0%	600	596	4	120
All providers	glm-5.3-flash	qwen3.8-27b	task_success	-7.9%	-11.9% to -4.2%	600	596	4	120
All providers	glm-5.3-flash	qwen3.8-27b	decision_correct	1.3%	-0.7% to 3.5%	600	596	4	120
All providers	gpt-5.6-luna	gpt-5.6-sol	fact_f1	-9.6%	-12.0% to -7.4%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-sol	exact_world	-25.8%	-30.3% to -21.3%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-sol	task_success	-26.8%	-31.3% to -22.2%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-sol	decision_correct	-2.8%	-4.3% to -1.5%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-terra	fact_f1	-0.4%	-3.1% to 2.1%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-terra	exact_world	-8.0%	-12.5% to -3.8%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-terra	task_success	-9.0%	-13.3% to -5.0%	600	600	0	120
All providers	gpt-5.6-luna	gpt-5.6-terra	decision_correct	-2.7%	-4.2% to -1.5%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-astra	fact_f1	-17.0%	-19.1% to -14.9%	600	550	50	115
All providers	gpt-5.6-luna	gpt-6-astra	exact_world	-44.0%	-48.8% to -39.1%	600	550	50	115
All providers	gpt-5.6-luna	gpt-6-astra	task_success	-44.7%	-49.6% to -39.8%	600	550	50	115
All providers	gpt-5.6-luna	gpt-6-astra	decision_correct	-2.4%	-3.7% to -1.1%	600	550	50	115
All providers	gpt-5.6-luna	gpt-6-luna	fact_f1	-0.1%	-2.8% to 2.5%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-luna	exact_world	0.2%	-4.0% to 4.3%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-luna	task_success	-0.7%	-4.8% to 3.5%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-luna	decision_correct	-1.2%	-2.7% to 0.3%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-sol	fact_f1	-15.3%	-17.5% to -13.1%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-sol	exact_world	-31.7%	-36.5% to -26.7%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-sol	task_success	-32.5%	-37.5% to -27.3%	600	600	0	120
All providers	gpt-5.6-luna	gpt-6-sol	decision_correct	-1.3%	-2.7% to -0.2%	600	600	0	120
All providers	gpt-5.6-luna	grok-4.6	fact_f1	-8.1%	-10.4% to -5.8%	600	600	0	120
All providers	gpt-5.6-luna	grok-4.6	exact_world	5.7%	0.7% to 10.7%	600	600	0	120
All providers	gpt-5.6-luna	grok-4.6	task_success	4.7%	-0.5% to 9.5%	600	600	0	120
All providers	gpt-5.6-luna	grok-4.6	decision_correct	0.5%	-1.5% to 2.5%	600	600	0	120
All providers	gpt-5.6-luna	kimi-k2.6	fact_f1	-9.2%	-11.3% to -7.1%	600	599	1	120
All providers	gpt-5.6-luna	kimi-k2.6	exact_world	6.2%	1.5% to 10.7%	600	599	1	120
All providers	gpt-5.6-luna	kimi-k2.6	task_success	5.2%	0.7% to 9.7%	600	599	1	120
All providers	gpt-5.6-luna	kimi-k2.6	decision_correct	-0.7%	-2.5% to 1.0%	600	599	1	120
All providers	gpt-5.6-luna	kimi-k3	fact_f1	-2.3%	-6.1% to 1.4%	600	443	157	96
All providers	gpt-5.6-luna	kimi-k3	exact_world	2.0%	-3.9% to 7.9%	600	443	157	96
All providers	gpt-5.6-luna	kimi-k3	task_success	1.4%	-4.6% to 7.3%	600	443	157	96
All providers	gpt-5.6-luna	kimi-k3	decision_correct	-2.5%	-4.1% to -1.1%	600	443	157	96
All providers	gpt-5.6-luna	mimo-v2.6-flash	fact_f1	2.0%	-0.9% to 4.7%	600	594	6	120
All providers	gpt-5.6-luna	mimo-v2.6-flash	exact_world	2.0%	-2.7% to 6.4%	600	594	6	120
All providers	gpt-5.6-luna	mimo-v2.6-flash	task_success	2.7%	-2.0% to 7.0%	600	594	6	120
All providers	gpt-5.6-luna	mimo-v2.6-flash	decision_correct	7.2%	4.7% to 9.9%	600	594	6	120
All providers	gpt-5.6-luna	mimo-v2.6-pro	fact_f1	4.8%	1.9% to 7.7%	600	600	0	120
All providers	gpt-5.6-luna	mimo-v2.6-pro	exact_world	3.5%	-1.2% to 8.2%	600	600	0	120
All providers	gpt-5.6-luna	mimo-v2.6-pro	task_success	3.7%	-1.0% to 8.7%	600	600	0	120
All providers	gpt-5.6-luna	mimo-v2.6-pro	decision_correct	8.7%	5.8% to 11.8%	600	600	0	120
All providers	gpt-5.6-luna	minimax-m3	fact_f1	12.9%	9.5% to 16.0%	600	600	0	120
All providers	gpt-5.6-luna	minimax-m3	exact_world	8.8%	4.5% to 13.2%	600	600	0	120
All providers	gpt-5.6-luna	minimax-m3	task_success	7.8%	3.7% to 12.2%	600	600	0	120
All providers	gpt-5.6-luna	minimax-m3	decision_correct	0.5%	-1.5% to 2.5%	600	600	0	120
All providers	gpt-5.6-luna	qwen3.8-27b	fact_f1	-2.3%	-5.1% to 0.6%	600	600	0	120
All providers	gpt-5.6-luna	qwen3.8-27b	exact_world	9.0%	4.3% to 13.7%	600	600	0	120
All providers	gpt-5.6-luna	qwen3.8-27b	task_success	8.0%	3.2% to 12.5%	600	600	0	120
All providers	gpt-5.6-luna	qwen3.8-27b	decision_correct	0.2%	-1.7% to 2.2%	600	600	0	120
All providers	gpt-5.6-sol	gpt-5.6-terra	fact_f1	9.3%	7.2% to 11.3%	600	600	0	120
All providers	gpt-5.6-sol	gpt-5.6-terra	exact_world	17.8%	13.3% to 22.2%	600	600	0	120
All providers	gpt-5.6-sol	gpt-5.6-terra	task_success	17.8%	13.3% to 22.2%	600	600	0	120
All providers	gpt-5.6-sol	gpt-5.6-terra	decision_correct	0.2%	0.0% to 0.5%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-astra	fact_f1	-6.9%	-8.7% to -5.1%	600	550	50	115
All providers	gpt-5.6-sol	gpt-6-astra	exact_world	-18.0%	-23.1% to -12.9%	600	550	50	115
All providers	gpt-5.6-sol	gpt-6-astra	task_success	-18.0%	-23.1% to -12.9%	600	550	50	115
All providers	gpt-5.6-sol	gpt-6-astra	decision_correct	0.0%	0.0% to 0.0%	600	550	50	115
All providers	gpt-5.6-sol	gpt-6-luna	fact_f1	9.5%	7.0% to 11.9%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-luna	exact_world	26.0%	21.0% to 30.8%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-luna	task_success	26.2%	21.3% to 31.0%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-luna	decision_correct	1.7%	0.7% to 2.7%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-sol	fact_f1	-5.6%	-7.5% to -3.8%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-sol	exact_world	-5.8%	-10.3% to -1.2%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-sol	task_success	-5.7%	-10.3% to -1.0%	600	600	0	120
All providers	gpt-5.6-sol	gpt-6-sol	decision_correct	1.5%	0.7% to 2.5%	600	600	0	120
All providers	gpt-5.6-sol	grok-4.6	fact_f1	1.5%	-0.4% to 3.5%	600	600	0	120
All providers	gpt-5.6-sol	grok-4.6	exact_world	31.5%	25.7% to 36.8%	600	600	0	120
All providers	gpt-5.6-sol	grok-4.6	task_success	31.5%	25.7% to 36.8%	600	600	0	120
All providers	gpt-5.6-sol	grok-4.6	decision_correct	3.3%	1.3% to 5.5%	600	600	0	120
All providers	gpt-5.6-sol	kimi-k2.6	fact_f1	0.4%	-1.3% to 2.1%	600	599	1	120
All providers	gpt-5.6-sol	kimi-k2.6	exact_world	31.9%	25.5% to 37.7%	600	599	1	120
All providers	gpt-5.6-sol	kimi-k2.6	task_success	31.9%	25.5% to 37.7%	600	599	1	120
All providers	gpt-5.6-sol	kimi-k2.6	decision_correct	2.2%	1.0% to 3.5%	600	599	1	120
All providers	gpt-5.6-sol	kimi-k3	fact_f1	7.6%	4.6% to 10.4%	600	443	157	96
All providers	gpt-5.6-sol	kimi-k3	exact_world	25.5%	18.7% to 32.0%	600	443	157	96
All providers	gpt-5.6-sol	kimi-k3	task_success	25.5%	18.7% to 32.0%	600	443	157	96
All providers	gpt-5.6-sol	kimi-k3	decision_correct	0.2%	0.0% to 0.7%	600	443	157	96
All providers	gpt-5.6-sol	mimo-v2.6-flash	fact_f1	11.6%	9.3% to 14.0%	600	594	6	120
All providers	gpt-5.6-sol	mimo-v2.6-flash	exact_world	27.3%	21.4% to 32.4%	600	594	6	120
All providers	gpt-5.6-sol	mimo-v2.6-flash	task_success	29.0%	22.9% to 34.2%	600	594	6	120
All providers	gpt-5.6-sol	mimo-v2.6-flash	decision_correct	10.1%	7.5% to 12.9%	600	594	6	120
All providers	gpt-5.6-sol	mimo-v2.6-pro	fact_f1	14.4%	11.8% to 17.2%	600	600	0	120
All providers	gpt-5.6-sol	mimo-v2.6-pro	exact_world	29.3%	24.2% to 34.3%	600	600	0	120
All providers	gpt-5.6-sol	mimo-v2.6-pro	task_success	30.5%	25.3% to 35.7%	600	600	0	120
All providers	gpt-5.6-sol	mimo-v2.6-pro	decision_correct	11.5%	8.8% to 14.3%	600	600	0	120
All providers	gpt-5.6-sol	minimax-m3	fact_f1	22.6%	19.5% to 25.6%	600	600	0	120
All providers	gpt-5.6-sol	minimax-m3	exact_world	34.7%	28.8% to 40.3%	600	600	0	120
All providers	gpt-5.6-sol	minimax-m3	task_success	34.7%	28.8% to 40.3%	600	600	0	120
All providers	gpt-5.6-sol	minimax-m3	decision_correct	3.3%	1.8% to 5.0%	600	600	0	120
All providers	gpt-5.6-sol	qwen3.8-27b	fact_f1	7.4%	5.1% to 9.7%	600	600	0	120
All providers	gpt-5.6-sol	qwen3.8-27b	exact_world	34.8%	28.3% to 40.8%	600	600	0	120
All providers	gpt-5.6-sol	qwen3.8-27b	task_success	34.8%	28.3% to 40.8%	600	600	0	120
All providers	gpt-5.6-sol	qwen3.8-27b	decision_correct	3.0%	1.5% to 4.8%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-astra	fact_f1	-15.6%	-17.9% to -13.4%	600	550	50	115
All providers	gpt-5.6-terra	gpt-6-astra	exact_world	-35.1%	-40.0% to -29.8%	600	550	50	115
All providers	gpt-5.6-terra	gpt-6-astra	task_success	-35.1%	-40.0% to -29.8%	600	550	50	115
All providers	gpt-5.6-terra	gpt-6-astra	decision_correct	0.0%	0.0% to 0.0%	600	550	50	115
All providers	gpt-5.6-terra	gpt-6-luna	fact_f1	0.3%	-2.1% to 2.6%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-luna	exact_world	8.2%	3.7% to 12.7%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-luna	task_success	8.3%	3.8% to 12.7%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-luna	decision_correct	1.5%	0.5% to 2.5%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-sol	fact_f1	-14.9%	-17.2% to -12.5%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-sol	exact_world	-23.7%	-28.5% to -18.5%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-sol	task_success	-23.5%	-28.3% to -18.5%	600	600	0	120
All providers	gpt-5.6-terra	gpt-6-sol	decision_correct	1.3%	0.5% to 2.3%	600	600	0	120
All providers	gpt-5.6-terra	grok-4.6	fact_f1	-7.7%	-9.9% to -5.4%	600	600	0	120
All providers	gpt-5.6-terra	grok-4.6	exact_world	13.7%	8.7% to 18.7%	600	600	0	120
All providers	gpt-5.6-terra	grok-4.6	task_success	13.7%	8.7% to 18.7%	600	600	0	120
All providers	gpt-5.6-terra	grok-4.6	decision_correct	3.2%	1.3% to 5.2%	600	600	0	120
All providers	gpt-5.6-terra	kimi-k2.6	fact_f1	-8.8%	-10.9% to -6.8%	600	599	1	120
All providers	gpt-5.6-terra	kimi-k2.6	exact_world	14.0%	9.2% to 19.0%	600	599	1	120
All providers	gpt-5.6-terra	kimi-k2.6	task_success	14.0%	9.2% to 19.0%	600	599	1	120
All providers	gpt-5.6-terra	kimi-k2.6	decision_correct	2.0%	0.7% to 3.5%	600	599	1	120
All providers	gpt-5.6-terra	kimi-k3	fact_f1	-0.9%	-3.6% to 2.0%	600	443	157	96
All providers	gpt-5.6-terra	kimi-k3	exact_world	9.3%	4.0% to 14.8%	600	443	157	96
All providers	gpt-5.6-terra	kimi-k3	task_success	9.3%	4.0% to 14.8%	600	443	157	96
All providers	gpt-5.6-terra	kimi-k3	decision_correct	0.0%	0.0% to 0.0%	600	443	157	96
All providers	gpt-5.6-terra	mimo-v2.6-flash	fact_f1	2.3%	-0.2% to 4.7%	600	594	6	120
All providers	gpt-5.6-terra	mimo-v2.6-flash	exact_world	9.6%	5.4% to 13.5%	600	594	6	120
All providers	gpt-5.6-terra	mimo-v2.6-flash	task_success	11.3%	7.1% to 15.2%	600	594	6	120
All providers	gpt-5.6-terra	mimo-v2.6-flash	decision_correct	9.9%	7.4% to 12.8%	600	594	6	120
All providers	gpt-5.6-terra	mimo-v2.6-pro	fact_f1	5.2%	2.6% to 7.7%	600	600	0	120
All providers	gpt-5.6-terra	mimo-v2.6-pro	exact_world	11.5%	7.3% to 15.8%	600	600	0	120
All providers	gpt-5.6-terra	mimo-v2.6-pro	task_success	12.7%	8.3% to 17.3%	600	600	0	120
All providers	gpt-5.6-terra	mimo-v2.6-pro	decision_correct	11.3%	8.5% to 14.3%	600	600	0	120
All providers	gpt-5.6-terra	minimax-m3	fact_f1	13.3%	10.3% to 16.5%	600	600	0	120
All providers	gpt-5.6-terra	minimax-m3	exact_world	16.8%	12.0% to 21.5%	600	600	0	120
All providers	gpt-5.6-terra	minimax-m3	task_success	16.8%	12.0% to 21.5%	600	600	0	120
All providers	gpt-5.6-terra	minimax-m3	decision_correct	3.2%	1.8% to 4.7%	600	600	0	120
All providers	gpt-5.6-terra	qwen3.8-27b	fact_f1	-1.9%	-4.2% to 0.5%	600	600	0	120
All providers	gpt-5.6-terra	qwen3.8-27b	exact_world	17.0%	12.3% to 21.3%	600	600	0	120
All providers	gpt-5.6-terra	qwen3.8-27b	task_success	17.0%	12.3% to 21.3%	600	600	0	120
All providers	gpt-5.6-terra	qwen3.8-27b	decision_correct	2.8%	1.3% to 4.5%	600	600	0	120
All providers	gpt-6-astra	gpt-6-luna	fact_f1	16.3%	14.0% to 18.7%	600	550	50	115
All providers	gpt-6-astra	gpt-6-luna	exact_world	44.0%	38.7% to 48.8%	600	550	50	115
All providers	gpt-6-astra	gpt-6-luna	task_success	44.2%	39.0% to 49.0%	600	550	50	115
All providers	gpt-6-astra	gpt-6-luna	decision_correct	1.5%	0.5% to 2.5%	600	550	50	115
All providers	gpt-6-astra	gpt-6-sol	fact_f1	2.0%	1.3% to 2.7%	600	550	50	115
All providers	gpt-6-astra	gpt-6-sol	exact_world	13.8%	9.5% to 18.3%	600	550	50	115
All providers	gpt-6-astra	gpt-6-sol	task_success	14.0%	9.6% to 18.5%	600	550	50	115
All providers	gpt-6-astra	gpt-6-sol	decision_correct	1.5%	0.6% to 2.5%	600	550	50	115
All providers	gpt-6-astra	grok-4.6	fact_f1	8.8%	7.6% to 10.1%	600	550	50	115
All providers	gpt-6-astra	grok-4.6	exact_world	49.8%	44.6% to 54.8%	600	550	50	115
All providers	gpt-6-astra	grok-4.6	task_success	49.8%	44.6% to 54.8%	600	550	50	115
All providers	gpt-6-astra	grok-4.6	decision_correct	3.5%	1.5% to 5.8%	600	550	50	115
All providers	gpt-6-astra	kimi-k2.6	fact_f1	7.9%	6.7% to 9.2%	600	549	51	115
All providers	gpt-6-astra	kimi-k2.6	exact_world	49.5%	43.8% to 55.2%	600	549	51	115
All providers	gpt-6-astra	kimi-k2.6	task_success	49.5%	43.8% to 55.2%	600	549	51	115
All providers	gpt-6-astra	kimi-k2.6	decision_correct	2.2%	0.9% to 3.7%	600	549	51	115
All providers	gpt-6-astra	kimi-k3	fact_f1	13.4%	10.7% to 16.3%	600	436	164	95
All providers	gpt-6-astra	kimi-k3	exact_world	42.9%	36.0% to 49.2%	600	436	164	95
All providers	gpt-6-astra	kimi-k3	task_success	42.9%	36.0% to 49.2%	600	436	164	95
All providers	gpt-6-astra	kimi-k3	decision_correct	0.2%	0.0% to 0.7%	600	436	164	95
All providers	gpt-6-astra	mimo-v2.6-flash	fact_f1	18.2%	15.7% to 20.6%	600	544	56	115
All providers	gpt-6-astra	mimo-v2.6-flash	exact_world	45.0%	39.4% to 50.0%	600	544	56	115
All providers	gpt-6-astra	mimo-v2.6-flash	task_success	46.9%	41.2% to 52.0%	600	544	56	115
All providers	gpt-6-astra	mimo-v2.6-flash	decision_correct	9.7%	7.1% to 12.7%	600	544	56	115
All providers	gpt-6-astra	mimo-v2.6-pro	fact_f1	20.5%	17.9% to 23.1%	600	550	50	115
All providers	gpt-6-astra	mimo-v2.6-pro	exact_world	46.2%	40.4% to 51.2%	600	550	50	115
All providers	gpt-6-astra	mimo-v2.6-pro	task_success	47.3%	41.2% to 52.5%	600	550	50	115
All providers	gpt-6-astra	mimo-v2.6-pro	decision_correct	10.7%	7.8% to 13.8%	600	550	50	115
All providers	gpt-6-astra	minimax-m3	fact_f1	28.2%	24.9% to 31.7%	600	550	50	115
All providers	gpt-6-astra	minimax-m3	exact_world	52.4%	46.6% to 57.7%	600	550	50	115
All providers	gpt-6-astra	minimax-m3	task_success	52.4%	46.6% to 57.7%	600	550	50	115
All providers	gpt-6-astra	minimax-m3	decision_correct	3.3%	1.8% to 4.9%	600	550	50	115
All providers	gpt-6-astra	qwen3.8-27b	fact_f1	13.8%	11.6% to 16.1%	600	550	50	115
All providers	gpt-6-astra	qwen3.8-27b	exact_world	52.7%	46.3% to 58.9%	600	550	50	115
All providers	gpt-6-astra	qwen3.8-27b	task_success	52.7%	46.3% to 58.9%	600	550	50	115
All providers	gpt-6-astra	qwen3.8-27b	decision_correct	3.1%	1.5% to 4.9%	600	550	50	115
All providers	gpt-6-luna	gpt-6-sol	fact_f1	-15.2%	-17.5% to -12.9%	600	600	0	120
All providers	gpt-6-luna	gpt-6-sol	exact_world	-31.8%	-36.5% to -27.2%	600	600	0	120
All providers	gpt-6-luna	gpt-6-sol	task_success	-31.8%	-36.5% to -27.2%	600	600	0	120
All providers	gpt-6-luna	gpt-6-sol	decision_correct	-0.2%	-1.5% to 1.2%	600	600	0	120
All providers	gpt-6-luna	grok-4.6	fact_f1	-8.0%	-10.3% to -5.7%	600	600	0	120
All providers	gpt-6-luna	grok-4.6	exact_world	5.5%	0.7% to 10.7%	600	600	0	120
All providers	gpt-6-luna	grok-4.6	task_success	5.3%	0.5% to 10.3%	600	600	0	120
All providers	gpt-6-luna	grok-4.6	decision_correct	1.7%	-0.5% to 4.0%	600	600	0	120
All providers	gpt-6-luna	kimi-k2.6	fact_f1	-9.1%	-11.5% to -6.7%	600	599	1	120
All providers	gpt-6-luna	kimi-k2.6	exact_world	6.0%	1.2% to 10.5%	600	599	1	120
All providers	gpt-6-luna	kimi-k2.6	task_success	5.8%	1.0% to 10.4%	600	599	1	120
All providers	gpt-6-luna	kimi-k2.6	decision_correct	0.5%	-1.2% to 2.2%	600	599	1	120
All providers	gpt-6-luna	kimi-k3	fact_f1	-1.1%	-4.5% to 2.1%	600	443	157	96
All providers	gpt-6-luna	kimi-k3	exact_world	2.0%	-4.2% to 8.3%	600	443	157	96
All providers	gpt-6-luna	kimi-k3	task_success	2.0%	-4.2% to 8.3%	600	443	157	96
All providers	gpt-6-luna	kimi-k3	decision_correct	-0.5%	-1.4% to 0.4%	600	443	157	96
All providers	gpt-6-luna	mimo-v2.6-flash	fact_f1	2.0%	-0.8% to 4.7%	600	594	6	120
All providers	gpt-6-luna	mimo-v2.6-flash	exact_world	1.5%	-3.0% to 5.7%	600	594	6	120
All providers	gpt-6-luna	mimo-v2.6-flash	task_success	3.0%	-1.4% to 7.3%	600	594	6	120
All providers	gpt-6-luna	mimo-v2.6-flash	decision_correct	8.4%	5.7% to 11.4%	600	594	6	120
All providers	gpt-6-luna	mimo-v2.6-pro	fact_f1	4.9%	2.0% to 7.7%	600	600	0	120
All providers	gpt-6-luna	mimo-v2.6-pro	exact_world	3.3%	-1.0% to 7.8%	600	600	0	120
All providers	gpt-6-luna	mimo-v2.6-pro	task_success	4.3%	-0.2% to 9.0%	600	600	0	120
All providers	gpt-6-luna	mimo-v2.6-pro	decision_correct	9.8%	7.2% to 12.8%	600	600	0	120
All providers	gpt-6-luna	minimax-m3	fact_f1	13.0%	9.8% to 16.4%	600	600	0	120
All providers	gpt-6-luna	minimax-m3	exact_world	8.7%	4.2% to 13.3%	600	600	0	120
All providers	gpt-6-luna	minimax-m3	task_success	8.5%	3.8% to 13.0%	600	600	0	120
All providers	gpt-6-luna	minimax-m3	decision_correct	1.7%	-0.2% to 3.5%	600	600	0	120
All providers	gpt-6-luna	qwen3.8-27b	fact_f1	-2.2%	-4.8% to 0.5%	600	600	0	120
All providers	gpt-6-luna	qwen3.8-27b	exact_world	8.8%	4.0% to 13.5%	600	600	0	120
All providers	gpt-6-luna	qwen3.8-27b	task_success	8.7%	3.8% to 13.5%	600	600	0	120
All providers	gpt-6-luna	qwen3.8-27b	decision_correct	1.3%	-0.5% to 3.3%	600	600	0	120
All providers	gpt-6-sol	grok-4.6	fact_f1	7.2%	5.9% to 8.4%	600	600	0	120
All providers	gpt-6-sol	grok-4.6	exact_world	37.3%	32.7% to 41.8%	600	600	0	120
All providers	gpt-6-sol	grok-4.6	task_success	37.2%	32.3% to 41.7%	600	600	0	120
All providers	gpt-6-sol	grok-4.6	decision_correct	1.8%	0.0% to 3.8%	600	600	0	120
All providers	gpt-6-sol	kimi-k2.6	fact_f1	6.1%	4.8% to 7.4%	600	599	1	120
All providers	gpt-6-sol	kimi-k2.6	exact_world	37.7%	32.4% to 43.1%	600	599	1	120
All providers	gpt-6-sol	kimi-k2.6	task_success	37.6%	32.2% to 42.9%	600	599	1	120
All providers	gpt-6-sol	kimi-k2.6	decision_correct	0.7%	-0.8% to 2.3%	600	599	1	120
All providers	gpt-6-sol	kimi-k3	fact_f1	11.3%	8.4% to 14.2%	600	443	157	96
All providers	gpt-6-sol	kimi-k3	exact_world	28.7%	22.6% to 34.9%	600	443	157	96
All providers	gpt-6-sol	kimi-k3	task_success	28.4%	22.4% to 34.7%	600	443	157	96
All providers	gpt-6-sol	kimi-k3	decision_correct	-1.6%	-2.8% to -0.7%	600	443	157	96
All providers	gpt-6-sol	mimo-v2.6-flash	fact_f1	17.3%	14.8% to 19.9%	600	594	6	120
All providers	gpt-6-sol	mimo-v2.6-flash	exact_world	33.2%	27.7% to 38.3%	600	594	6	120
All providers	gpt-6-sol	mimo-v2.6-flash	task_success	34.7%	29.0% to 40.1%	600	594	6	120
All providers	gpt-6-sol	mimo-v2.6-flash	decision_correct	8.6%	6.0% to 11.4%	600	594	6	120
All providers	gpt-6-sol	mimo-v2.6-pro	fact_f1	20.0%	17.3% to 22.8%	600	600	0	120
All providers	gpt-6-sol	mimo-v2.6-pro	exact_world	35.2%	30.0% to 39.8%	600	600	0	120
All providers	gpt-6-sol	mimo-v2.6-pro	task_success	36.2%	31.0% to 41.0%	600	600	0	120
All providers	gpt-6-sol	mimo-v2.6-pro	decision_correct	10.0%	7.0% to 13.2%	600	600	0	120
All providers	gpt-6-sol	minimax-m3	fact_f1	28.2%	24.6% to 31.5%	600	600	0	120
All providers	gpt-6-sol	minimax-m3	exact_world	40.5%	34.8% to 45.8%	600	600	0	120
All providers	gpt-6-sol	minimax-m3	task_success	40.3%	34.7% to 45.8%	600	600	0	120
All providers	gpt-6-sol	minimax-m3	decision_correct	1.8%	0.3% to 3.3%	600	600	0	120
All providers	gpt-6-sol	qwen3.8-27b	fact_f1	13.0%	10.8% to 15.5%	600	600	0	120
All providers	gpt-6-sol	qwen3.8-27b	exact_world	40.7%	34.7% to 46.5%	600	600	0	120
All providers	gpt-6-sol	qwen3.8-27b	task_success	40.5%	34.3% to 46.2%	600	600	0	120
All providers	gpt-6-sol	qwen3.8-27b	decision_correct	1.5%	0.0% to 3.3%	600	600	0	120
All providers	grok-4.6	kimi-k2.6	fact_f1	-1.1%	-2.5% to 0.3%	600	599	1	120
All providers	grok-4.6	kimi-k2.6	exact_world	0.3%	-3.7% to 4.3%	600	599	1	120
All providers	grok-4.6	kimi-k2.6	task_success	0.3%	-3.7% to 4.3%	600	599	1	120
All providers	grok-4.6	kimi-k2.6	decision_correct	-1.2%	-3.5% to 1.0%	600	599	1	120
All providers	grok-4.6	kimi-k3	fact_f1	5.1%	2.1% to 8.2%	600	443	157	96
All providers	grok-4.6	kimi-k3	exact_world	-5.6%	-11.3% to 0.0%	600	443	157	96
All providers	grok-4.6	kimi-k3	task_success	-5.6%	-11.3% to 0.0%	600	443	157	96
All providers	grok-4.6	kimi-k3	decision_correct	-3.8%	-6.7% to -1.4%	600	443	157	96
All providers	grok-4.6	mimo-v2.6-flash	fact_f1	10.3%	7.8% to 12.7%	600	594	6	120
All providers	grok-4.6	mimo-v2.6-flash	exact_world	-3.7%	-8.8% to 1.2%	600	594	6	120
All providers	grok-4.6	mimo-v2.6-flash	task_success	-2.0%	-6.9% to 3.0%	600	594	6	120
All providers	grok-4.6	mimo-v2.6-flash	decision_correct	6.9%	3.7% to 10.4%	600	594	6	120
All providers	grok-4.6	mimo-v2.6-pro	fact_f1	12.9%	10.4% to 15.5%	600	600	0	120
All providers	grok-4.6	mimo-v2.6-pro	exact_world	-2.2%	-6.5% to 2.7%	600	600	0	120
All providers	grok-4.6	mimo-v2.6-pro	task_success	-1.0%	-5.5% to 3.8%	600	600	0	120
All providers	grok-4.6	mimo-v2.6-pro	decision_correct	8.2%	4.7% to 11.8%	600	600	0	120
All providers	grok-4.6	minimax-m3	fact_f1	21.0%	17.8% to 24.2%	600	600	0	120
All providers	grok-4.6	minimax-m3	exact_world	3.2%	-1.3% to 7.7%	600	600	0	120
All providers	grok-4.6	minimax-m3	task_success	3.2%	-1.3% to 7.7%	600	600	0	120
All providers	grok-4.6	minimax-m3	decision_correct	0.0%	-2.3% to 2.2%	600	600	0	120
All providers	grok-4.6	qwen3.8-27b	fact_f1	5.8%	3.6% to 8.4%	600	600	0	120
All providers	grok-4.6	qwen3.8-27b	exact_world	3.3%	-1.3% to 8.0%	600	600	0	120
All providers	grok-4.6	qwen3.8-27b	task_success	3.3%	-1.3% to 8.0%	600	600	0	120
All providers	grok-4.6	qwen3.8-27b	decision_correct	-0.3%	-2.5% to 1.5%	600	600	0	120
All providers	kimi-k2.6	kimi-k3	fact_f1	6.2%	3.9% to 8.6%	600	443	157	96
All providers	kimi-k2.6	kimi-k3	exact_world	-2.7%	-7.8% to 2.6%	600	443	157	96
All providers	kimi-k2.6	kimi-k3	task_success	-2.7%	-7.8% to 2.6%	600	443	157	96
All providers	kimi-k2.6	kimi-k3	decision_correct	-2.5%	-4.4% to -0.9%	600	443	157	96
All providers	kimi-k2.6	mimo-v2.6-flash	fact_f1	11.3%	9.0% to 13.4%	600	593	7	120
All providers	kimi-k2.6	mimo-v2.6-flash	exact_world	-3.9%	-7.7% to 0.0%	600	593	7	120
All providers	kimi-k2.6	mimo-v2.6-flash	task_success	-2.2%	-6.1% to 1.8%	600	593	7	120
All providers	kimi-k2.6	mimo-v2.6-flash	decision_correct	7.9%	4.9% to 11.1%	600	593	7	120
All providers	kimi-k2.6	mimo-v2.6-pro	fact_f1	14.0%	11.6% to 16.6%	600	599	1	120
All providers	kimi-k2.6	mimo-v2.6-pro	exact_world	-2.5%	-6.2% to 1.3%	600	599	1	120
All providers	kimi-k2.6	mimo-v2.6-pro	task_success	-1.3%	-5.2% to 2.7%	600	599	1	120
All providers	kimi-k2.6	mimo-v2.6-pro	decision_correct	9.3%	6.2% to 12.8%	600	599	1	120
All providers	kimi-k2.6	minimax-m3	fact_f1	22.1%	19.0% to 25.2%	600	599	1	120
All providers	kimi-k2.6	minimax-m3	exact_world	2.7%	-1.3% to 6.5%	600	599	1	120
All providers	kimi-k2.6	minimax-m3	task_success	2.7%	-1.3% to 6.5%	600	599	1	120
All providers	kimi-k2.6	minimax-m3	decision_correct	1.2%	-0.8% to 3.2%	600	599	1	120
All providers	kimi-k2.6	qwen3.8-27b	fact_f1	7.0%	4.9% to 9.1%	600	599	1	120
All providers	kimi-k2.6	qwen3.8-27b	exact_world	3.0%	-1.0% to 7.2%	600	599	1	120
All providers	kimi-k2.6	qwen3.8-27b	task_success	3.0%	-1.0% to 7.2%	600	599	1	120
All providers	kimi-k2.6	qwen3.8-27b	decision_correct	0.8%	-1.2% to 3.2%	600	599	1	120
All providers	kimi-k3	mimo-v2.6-flash	fact_f1	2.6%	-0.3% to 5.3%	600	437	163	96
All providers	kimi-k3	mimo-v2.6-flash	exact_world	-1.8%	-6.7% to 2.8%	600	437	163	96
All providers	kimi-k3	mimo-v2.6-flash	task_success	-0.2%	-5.1% to 4.4%	600	437	163	96
All providers	kimi-k3	mimo-v2.6-flash	decision_correct	8.5%	6.0% to 11.2%	600	437	163	96
All providers	kimi-k3	mimo-v2.6-pro	fact_f1	3.9%	1.2% to 6.8%	600	443	157	96
All providers	kimi-k3	mimo-v2.6-pro	exact_world	-1.6%	-6.2% to 2.9%	600	443	157	96
All providers	kimi-k3	mimo-v2.6-pro	task_success	-0.7%	-5.3% to 3.9%	600	443	157	96
All providers	kimi-k3	mimo-v2.6-pro	decision_correct	7.9%	5.1% to 10.9%	600	443	157	96
All providers	kimi-k3	minimax-m3	fact_f1	12.6%	8.8% to 16.7%	600	443	157	96
All providers	kimi-k3	minimax-m3	exact_world	5.6%	0.9% to 10.2%	600	443	157	96
All providers	kimi-k3	minimax-m3	task_success	5.6%	0.9% to 10.2%	600	443	157	96
All providers	kimi-k3	minimax-m3	decision_correct	3.6%	1.9% to 5.5%	600	443	157	96
All providers	kimi-k3	qwen3.8-27b	fact_f1	-1.0%	-4.0% to 2.1%	600	443	157	96
All providers	kimi-k3	qwen3.8-27b	exact_world	6.1%	1.4% to 11.0%	600	443	157	96
All providers	kimi-k3	qwen3.8-27b	task_success	6.1%	1.4% to 11.0%	600	443	157	96
All providers	kimi-k3	qwen3.8-27b	decision_correct	3.4%	1.6% to 5.6%	600	443	157	96
All providers	mimo-v2.6-flash	mimo-v2.6-pro	fact_f1	2.9%	0.5% to 5.5%	600	594	6	120
All providers	mimo-v2.6-flash	mimo-v2.6-pro	exact_world	2.0%	-1.7% to 5.9%	600	594	6	120
All providers	mimo-v2.6-flash	mimo-v2.6-pro	task_success	1.5%	-2.2% to 5.4%	600	594	6	120
All providers	mimo-v2.6-flash	mimo-v2.6-pro	decision_correct	1.5%	-1.8% to 5.0%	600	594	6	120
All providers	mimo-v2.6-flash	minimax-m3	fact_f1	10.9%	7.9% to 14.0%	600	594	6	120
All providers	mimo-v2.6-flash	minimax-m3	exact_world	7.1%	3.4% to 11.0%	600	594	6	120
All providers	mimo-v2.6-flash	minimax-m3	task_success	5.4%	1.5% to 9.4%	600	594	6	120
All providers	mimo-v2.6-flash	minimax-m3	decision_correct	-6.9%	-9.8% to -4.2%	600	594	6	120
All providers	mimo-v2.6-flash	qwen3.8-27b	fact_f1	-4.2%	-6.7% to -1.6%	600	594	6	120
All providers	mimo-v2.6-flash	qwen3.8-27b	exact_world	7.2%	3.4% to 11.3%	600	594	6	120
All providers	mimo-v2.6-flash	qwen3.8-27b	task_success	5.6%	1.7% to 9.8%	600	594	6	120
All providers	mimo-v2.6-flash	qwen3.8-27b	decision_correct	-7.1%	-10.1% to -4.0%	600	594	6	120
All providers	mimo-v2.6-pro	minimax-m3	fact_f1	8.1%	5.0% to 11.4%	600	600	0	120
All providers	mimo-v2.6-pro	minimax-m3	exact_world	5.3%	1.2% to 9.2%	600	600	0	120
All providers	mimo-v2.6-pro	minimax-m3	task_success	4.2%	-0.2% to 8.2%	600	600	0	120
All providers	mimo-v2.6-pro	minimax-m3	decision_correct	-8.2%	-11.7% to -4.8%	600	600	0	120
All providers	mimo-v2.6-pro	qwen3.8-27b	fact_f1	-7.0%	-9.9% to -4.2%	600	600	0	120
All providers	mimo-v2.6-pro	qwen3.8-27b	exact_world	5.5%	1.2% to 9.8%	600	600	0	120
All providers	mimo-v2.6-pro	qwen3.8-27b	task_success	4.3%	-0.2% to 8.8%	600	600	0	120
All providers	mimo-v2.6-pro	qwen3.8-27b	decision_correct	-8.5%	-12.0% to -5.0%	600	600	0	120
All providers	minimax-m3	qwen3.8-27b	fact_f1	-15.2%	-18.3% to -12.1%	600	600	0	120
All providers	minimax-m3	qwen3.8-27b	exact_world	0.2%	-3.7% to 4.0%	600	600	0	120
All providers	minimax-m3	qwen3.8-27b	task_success	0.2%	-3.7% to 4.0%	600	600	0	120
All providers	minimax-m3	qwen3.8-27b	decision_correct	-0.3%	-2.0% to 1.3%	600	600	0	120

conditions
Provider	Left	Right	Metric	Difference (pp)	95% CI (pp)	Expected pairs	Complete pairs	Missing pairs	Families
baseline:constraint-solver	explicit	formal	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	formal	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	formal	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	formal	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	formal	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	formal	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:constraint-solver	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	formal	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	formal	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	formal	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	formal	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	formal	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	formal	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:direct-facts	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	formal	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	formal	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	formal	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	formal	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	formal	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	formal	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:forward-chain	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	formal	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	formal	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	formal	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	formal	implicit	fact_f1	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	formal	implicit	exact_world	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	formal	implicit	task_success	0.0%	0.0% to 0.0%	120	120	0	120
baseline:story-copy	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
claude-fable-5	explicit	formal	fact_f1	-7.5%	-10.5% to -4.9%	120	44	76	44
claude-fable-5	explicit	formal	exact_world	-52.3%	-63.6% to -40.9%	120	44	76	44
claude-fable-5	explicit	formal	task_success	-52.3%	-63.6% to -40.9%	120	44	76	44
claude-fable-5	explicit	formal	decision_correct	-3.4%	-8.0% to 0.0%	120	44	76	44
claude-fable-5	explicit	implicit	fact_f1	-0.9%	-3.1% to 1.2%	120	32	88	32
claude-fable-5	explicit	implicit	exact_world	0.0%	-10.9% to 10.9%	120	32	88	32
claude-fable-5	explicit	implicit	task_success	0.0%	-10.9% to 10.9%	120	32	88	32
claude-fable-5	explicit	implicit	decision_correct	-1.6%	-4.7% to 0.0%	120	32	88	32
claude-fable-5	formal	implicit	fact_f1	6.7%	4.6% to 8.9%	120	32	88	32
claude-fable-5	formal	implicit	exact_world	56.2%	43.8% to 68.8%	120	32	88	32
claude-fable-5	formal	implicit	task_success	56.2%	43.8% to 68.8%	120	32	88	32
claude-fable-5	formal	implicit	decision_correct	3.1%	0.0% to 7.8%	120	32	88	32
claude-fable-5.1	explicit	formal	fact_f1	—	—	120	0	120	0
claude-fable-5.1	explicit	formal	exact_world	—	—	120	0	120	0
claude-fable-5.1	explicit	formal	task_success	—	—	120	0	120	0
claude-fable-5.1	explicit	formal	decision_correct	—	—	120	0	120	0
claude-fable-5.1	explicit	implicit	fact_f1	—	—	120	0	120	0
claude-fable-5.1	explicit	implicit	exact_world	—	—	120	0	120	0
claude-fable-5.1	explicit	implicit	task_success	—	—	120	0	120	0
claude-fable-5.1	explicit	implicit	decision_correct	—	—	120	0	120	0
claude-fable-5.1	formal	implicit	fact_f1	—	—	120	0	120	0
claude-fable-5.1	formal	implicit	exact_world	—	—	120	0	120	0
claude-fable-5.1	formal	implicit	task_success	—	—	120	0	120	0
claude-fable-5.1	formal	implicit	decision_correct	—	—	120	0	120	0
claude-haiku-4.5	explicit	formal	fact_f1	-30.4%	-34.8% to -26.0%	120	120	0	120
claude-haiku-4.5	explicit	formal	exact_world	-92.5%	-96.2% to -88.3%	120	120	0	120
claude-haiku-4.5	explicit	formal	task_success	-92.5%	-96.2% to -88.3%	120	120	0	120
claude-haiku-4.5	explicit	formal	decision_correct	-2.9%	-6.7% to 0.8%	120	120	0	120
claude-haiku-4.5	explicit	implicit	fact_f1	15.0%	11.3% to 18.6%	120	120	0	120
claude-haiku-4.5	explicit	implicit	exact_world	1.7%	-2.1% to 5.4%	120	120	0	120
claude-haiku-4.5	explicit	implicit	task_success	1.7%	-2.1% to 5.4%	120	120	0	120
claude-haiku-4.5	explicit	implicit	decision_correct	1.2%	-2.5% to 5.0%	120	120	0	120
claude-haiku-4.5	formal	implicit	fact_f1	45.4%	40.3% to 50.1%	120	120	0	120
claude-haiku-4.5	formal	implicit	exact_world	94.2%	90.4% to 97.1%	120	120	0	120
claude-haiku-4.5	formal	implicit	task_success	94.2%	90.4% to 97.1%	120	120	0	120
claude-haiku-4.5	formal	implicit	decision_correct	4.2%	0.4% to 7.9%	120	120	0	120
claude-opus-5	explicit	formal	fact_f1	—	—	120	0	120	0
claude-opus-5	explicit	formal	exact_world	—	—	120	0	120	0
claude-opus-5	explicit	formal	task_success	—	—	120	0	120	0
claude-opus-5	explicit	formal	decision_correct	—	—	120	0	120	0
claude-opus-5	explicit	implicit	fact_f1	10.1%	3.9% to 16.8%	120	85	35	85
claude-opus-5	explicit	implicit	exact_world	18.2%	8.8% to 27.1%	120	85	35	85
claude-opus-5	explicit	implicit	task_success	18.2%	8.8% to 27.1%	120	85	35	85
claude-opus-5	explicit	implicit	decision_correct	0.0%	-5.9% to 6.5%	120	85	35	85
claude-opus-5	formal	implicit	fact_f1	—	—	120	0	120	0
claude-opus-5	formal	implicit	exact_world	—	—	120	0	120	0
claude-opus-5	formal	implicit	task_success	—	—	120	0	120	0
claude-opus-5	formal	implicit	decision_correct	—	—	120	0	120	0
claude-opus-5.5	explicit	formal	fact_f1	-7.2%	-8.3% to -6.1%	120	115	5	115
claude-opus-5.5	explicit	formal	exact_world	-71.3%	-77.0% to -65.6%	120	115	5	115
claude-opus-5.5	explicit	formal	task_success	-71.7%	-77.4% to -65.7%	120	115	5	115
claude-opus-5.5	explicit	formal	decision_correct	-4.8%	-7.8% to -2.2%	120	115	5	115
claude-opus-5.5	explicit	implicit	fact_f1	2.5%	0.8% to 4.3%	120	113	7	113
claude-opus-5.5	explicit	implicit	exact_world	7.5%	0.9% to 14.2%	120	113	7	113
claude-opus-5.5	explicit	implicit	task_success	7.1%	0.0% to 13.7%	120	113	7	113
claude-opus-5.5	explicit	implicit	decision_correct	2.2%	-0.9% to 5.3%	120	113	7	113
claude-opus-5.5	formal	implicit	fact_f1	9.6%	8.1% to 11.2%	120	116	4	116
claude-opus-5.5	formal	implicit	exact_world	78.0%	72.4% to 83.6%	120	116	4	116
claude-opus-5.5	formal	implicit	task_success	78.0%	72.4% to 83.6%	120	116	4	116
claude-opus-5.5	formal	implicit	decision_correct	6.5%	3.9% to 9.5%	120	116	4	116
claude-sonnet-5	explicit	formal	fact_f1	-0.4%	-6.2% to 6.0%	120	86	34	86
claude-sonnet-5	explicit	formal	exact_world	-51.7%	-59.9% to -42.4%	120	86	34	86
claude-sonnet-5	explicit	formal	task_success	-51.7%	-59.9% to -42.4%	120	86	34	86
claude-sonnet-5	explicit	formal	decision_correct	4.1%	-1.7% to 10.5%	120	86	34	86
claude-sonnet-5	explicit	implicit	fact_f1	9.4%	3.1% to 15.5%	120	52	68	52
claude-sonnet-5	explicit	implicit	exact_world	-1.0%	-11.5% to 9.6%	120	52	68	52
claude-sonnet-5	explicit	implicit	task_success	-1.0%	-11.5% to 9.6%	120	52	68	52
claude-sonnet-5	explicit	implicit	decision_correct	-1.0%	-5.8% to 3.8%	120	52	68	52
claude-sonnet-5	formal	implicit	fact_f1	7.6%	-1.8% to 16.5%	120	52	68	52
claude-sonnet-5	formal	implicit	exact_world	50.0%	38.5% to 61.5%	120	52	68	52
claude-sonnet-5	formal	implicit	task_success	50.0%	38.5% to 61.5%	120	52	68	52
claude-sonnet-5	formal	implicit	decision_correct	-5.8%	-15.4% to 2.9%	120	52	68	52
deepseek-4.1-flash	explicit	formal	fact_f1	-4.5%	-5.9% to -3.3%	120	116	4	116
deepseek-4.1-flash	explicit	formal	exact_world	-44.8%	-52.2% to -37.5%	120	116	4	116
deepseek-4.1-flash	explicit	formal	task_success	-44.8%	-52.2% to -37.5%	120	116	4	116
deepseek-4.1-flash	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	116	4	116
deepseek-4.1-flash	explicit	implicit	fact_f1	41.9%	36.4% to 47.2%	120	115	5	115
deepseek-4.1-flash	explicit	implicit	exact_world	37.0%	29.6% to 45.2%	120	115	5	115
deepseek-4.1-flash	explicit	implicit	task_success	37.0%	29.6% to 45.2%	120	115	5	115
deepseek-4.1-flash	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	115	5	115
deepseek-4.1-flash	formal	implicit	fact_f1	46.6%	41.4% to 52.1%	120	119	1	119
deepseek-4.1-flash	formal	implicit	exact_world	81.9%	76.5% to 87.8%	120	119	1	119
deepseek-4.1-flash	formal	implicit	task_success	81.9%	76.5% to 87.8%	120	119	1	119
deepseek-4.1-flash	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	119	1	119
deepseek-v4-pro	explicit	formal	fact_f1	-4.8%	-7.9% to -1.3%	120	120	0	120
deepseek-v4-pro	explicit	formal	exact_world	-58.8%	-65.4% to -52.1%	120	120	0	120
deepseek-v4-pro	explicit	formal	task_success	-58.8%	-65.4% to -52.1%	120	120	0	120
deepseek-v4-pro	explicit	formal	decision_correct	-2.9%	-6.7% to 1.2%	120	120	0	120
deepseek-v4-pro	explicit	implicit	fact_f1	5.4%	2.3% to 8.4%	120	120	0	120
deepseek-v4-pro	explicit	implicit	exact_world	19.6%	12.1% to 26.7%	120	120	0	120
deepseek-v4-pro	explicit	implicit	task_success	19.6%	12.1% to 26.7%	120	120	0	120
deepseek-v4-pro	explicit	implicit	decision_correct	-0.4%	-3.3% to 2.5%	120	120	0	120
deepseek-v4-pro	formal	implicit	fact_f1	10.2%	6.5% to 13.4%	120	120	0	120
deepseek-v4-pro	formal	implicit	exact_world	78.3%	71.7% to 84.2%	120	120	0	120
deepseek-v4-pro	formal	implicit	task_success	78.3%	71.7% to 84.2%	120	120	0	120
deepseek-v4-pro	formal	implicit	decision_correct	2.5%	-1.7% to 6.2%	120	120	0	120
gemini-3.6-flash	explicit	formal	fact_f1	-16.3%	-19.7% to -12.9%	120	120	0	120
gemini-3.6-flash	explicit	formal	exact_world	-57.1%	-63.7% to -50.0%	120	120	0	120
gemini-3.6-flash	explicit	formal	task_success	-57.1%	-63.7% to -50.0%	120	120	0	120
gemini-3.6-flash	explicit	formal	decision_correct	-1.7%	-3.3% to -0.4%	120	120	0	120
gemini-3.6-flash	explicit	implicit	fact_f1	18.8%	14.9% to 22.4%	120	120	0	120
gemini-3.6-flash	explicit	implicit	exact_world	26.7%	20.4% to 32.9%	120	120	0	120
gemini-3.6-flash	explicit	implicit	task_success	26.7%	20.4% to 32.9%	120	120	0	120
gemini-3.6-flash	explicit	implicit	decision_correct	-0.8%	-2.5% to 0.8%	120	120	0	120
gemini-3.6-flash	formal	implicit	fact_f1	35.0%	30.9% to 39.2%	120	120	0	120
gemini-3.6-flash	formal	implicit	exact_world	83.8%	77.9% to 88.8%	120	120	0	120
gemini-3.6-flash	formal	implicit	task_success	83.8%	77.9% to 88.8%	120	120	0	120
gemini-3.6-flash	formal	implicit	decision_correct	0.8%	0.0% to 2.5%	120	120	0	120
gemini-3.7-flash	explicit	formal	fact_f1	-3.1%	-4.5% to -2.0%	120	120	0	120
gemini-3.7-flash	explicit	formal	exact_world	-31.2%	-37.5% to -25.4%	120	120	0	120
gemini-3.7-flash	explicit	formal	task_success	-31.2%	-37.5% to -25.4%	120	120	0	120
gemini-3.7-flash	explicit	formal	decision_correct	-0.8%	-2.1% to 0.0%	120	120	0	120
gemini-3.7-flash	explicit	implicit	fact_f1	15.5%	11.6% to 19.2%	120	120	0	120
gemini-3.7-flash	explicit	implicit	exact_world	15.8%	7.5% to 23.3%	120	120	0	120
gemini-3.7-flash	explicit	implicit	task_success	15.8%	7.5% to 23.3%	120	120	0	120
gemini-3.7-flash	explicit	implicit	decision_correct	-0.4%	-1.2% to 0.0%	120	120	0	120
gemini-3.7-flash	formal	implicit	fact_f1	18.6%	14.8% to 22.6%	120	120	0	120
gemini-3.7-flash	formal	implicit	exact_world	47.1%	40.4% to 53.3%	120	120	0	120
gemini-3.7-flash	formal	implicit	task_success	47.1%	40.4% to 53.3%	120	120	0	120
gemini-3.7-flash	formal	implicit	decision_correct	0.4%	0.0% to 1.2%	120	120	0	120
gemini-3.8-flash	explicit	formal	fact_f1	-4.6%	-6.4% to -3.3%	120	119	1	119
gemini-3.8-flash	explicit	formal	exact_world	-41.2%	-48.3% to -34.0%	120	119	1	119
gemini-3.8-flash	explicit	formal	task_success	-41.2%	-48.3% to -34.0%	120	119	1	119
gemini-3.8-flash	explicit	formal	decision_correct	-0.8%	-2.1% to 0.0%	120	119	1	119
gemini-3.8-flash	explicit	implicit	fact_f1	24.5%	19.5% to 29.4%	120	118	2	118
gemini-3.8-flash	explicit	implicit	exact_world	19.1%	8.9% to 28.0%	120	118	2	118
gemini-3.8-flash	explicit	implicit	task_success	19.1%	8.9% to 28.0%	120	118	2	118
gemini-3.8-flash	explicit	implicit	decision_correct	-0.8%	-2.1% to 0.0%	120	118	2	118
gemini-3.8-flash	formal	implicit	fact_f1	29.2%	24.6% to 33.8%	120	119	1	119
gemini-3.8-flash	formal	implicit	exact_world	60.9%	53.4% to 68.1%	120	119	1	119
gemini-3.8-flash	formal	implicit	task_success	60.9%	53.4% to 68.1%	120	119	1	119
gemini-3.8-flash	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	119	1	119
glm-4.7-flash	explicit	formal	fact_f1	-26.3%	-33.2% to -19.0%	120	104	16	104
glm-4.7-flash	explicit	formal	exact_world	-74.0%	-81.7% to -65.9%	120	104	16	104
glm-4.7-flash	explicit	formal	task_success	-74.0%	-81.7% to -65.9%	120	104	16	104
glm-4.7-flash	explicit	formal	decision_correct	-9.6%	-16.8% to -2.9%	120	104	16	104
glm-4.7-flash	explicit	implicit	fact_f1	6.3%	0.9% to 11.9%	120	97	23	97
glm-4.7-flash	explicit	implicit	exact_world	4.6%	0.5% to 8.8%	120	97	23	97
glm-4.7-flash	explicit	implicit	task_success	4.6%	0.5% to 8.8%	120	97	23	97
glm-4.7-flash	explicit	implicit	decision_correct	3.6%	-2.6% to 10.8%	120	97	23	97
glm-4.7-flash	formal	implicit	fact_f1	33.9%	27.4% to 39.8%	120	107	13	107
glm-4.7-flash	formal	implicit	exact_world	78.0%	70.1% to 85.5%	120	107	13	107
glm-4.7-flash	formal	implicit	task_success	78.0%	70.1% to 85.5%	120	107	13	107
glm-4.7-flash	formal	implicit	decision_correct	14.5%	6.5% to 22.4%	120	107	13	107
glm-5.3	explicit	formal	fact_f1	-14.0%	-18.8% to -9.5%	120	97	23	97
glm-5.3	explicit	formal	exact_world	-46.4%	-54.6% to -38.1%	120	97	23	97
glm-5.3	explicit	formal	task_success	-46.4%	-54.6% to -38.1%	120	97	23	97
glm-5.3	explicit	formal	decision_correct	-2.6%	-5.7% to 0.0%	120	97	23	97
glm-5.3	explicit	implicit	fact_f1	6.2%	1.4% to 11.1%	120	91	29	91
glm-5.3	explicit	implicit	exact_world	16.5%	8.2% to 24.7%	120	91	29	91
glm-5.3	explicit	implicit	task_success	16.5%	8.2% to 24.7%	120	91	29	91
glm-5.3	explicit	implicit	decision_correct	1.1%	-3.3% to 5.5%	120	91	29	91
glm-5.3	formal	implicit	fact_f1	19.9%	14.4% to 25.1%	120	109	11	109
glm-5.3	formal	implicit	exact_world	60.1%	52.3% to 67.0%	120	109	11	109
glm-5.3	formal	implicit	task_success	60.1%	52.3% to 67.0%	120	109	11	109
glm-5.3	formal	implicit	decision_correct	2.8%	-0.9% to 6.4%	120	109	11	109
glm-5.3-flash	explicit	formal	fact_f1	-34.3%	-39.3% to -29.4%	120	116	4	116
glm-5.3-flash	explicit	formal	exact_world	-66.4%	-74.6% to -58.2%	120	116	4	116
glm-5.3-flash	explicit	formal	task_success	-66.8%	-75.0% to -58.6%	120	116	4	116
glm-5.3-flash	explicit	formal	decision_correct	-2.2%	-4.3% to -0.4%	120	116	4	116
glm-5.3-flash	explicit	implicit	fact_f1	12.7%	7.9% to 17.6%	120	116	4	116
glm-5.3-flash	explicit	implicit	exact_world	14.2%	9.1% to 19.8%	120	116	4	116
glm-5.3-flash	explicit	implicit	task_success	13.8%	8.6% to 19.4%	120	116	4	116
glm-5.3-flash	explicit	implicit	decision_correct	0.0%	-2.6% to 2.6%	120	116	4	116
glm-5.3-flash	formal	implicit	fact_f1	45.8%	41.1% to 50.6%	120	120	0	120
glm-5.3-flash	formal	implicit	exact_world	78.3%	71.2% to 85.0%	120	120	0	120
glm-5.3-flash	formal	implicit	task_success	78.3%	71.2% to 85.0%	120	120	0	120
glm-5.3-flash	formal	implicit	decision_correct	2.1%	0.4% to 4.2%	120	120	0	120
gpt-5.6-luna	explicit	formal	fact_f1	-5.5%	-6.5% to -4.6%	120	120	0	120
gpt-5.6-luna	explicit	formal	exact_world	-60.0%	-66.2% to -53.8%	120	120	0	120
gpt-5.6-luna	explicit	formal	task_success	-60.0%	-66.3% to -53.3%	120	120	0	120
gpt-5.6-luna	explicit	formal	decision_correct	-1.7%	-4.6% to 2.1%	120	120	0	120
gpt-5.6-luna	explicit	implicit	fact_f1	35.5%	30.3% to 40.8%	120	120	0	120
gpt-5.6-luna	explicit	implicit	exact_world	23.3%	16.7% to 30.4%	120	120	0	120
gpt-5.6-luna	explicit	implicit	task_success	21.7%	15.0% to 28.3%	120	120	0	120
gpt-5.6-luna	explicit	implicit	decision_correct	-0.4%	-3.3% to 2.5%	120	120	0	120
gpt-5.6-luna	formal	implicit	fact_f1	41.1%	36.0% to 46.1%	120	120	0	120
gpt-5.6-luna	formal	implicit	exact_world	83.3%	78.8% to 87.5%	120	120	0	120
gpt-5.6-luna	formal	implicit	task_success	81.7%	75.8% to 86.7%	120	120	0	120
gpt-5.6-luna	formal	implicit	decision_correct	1.2%	-2.1% to 4.2%	120	120	0	120
gpt-5.6-sol	explicit	formal	fact_f1	-2.8%	-3.6% to -2.1%	120	120	0	120
gpt-5.6-sol	explicit	formal	exact_world	-32.9%	-40.0% to -26.2%	120	120	0	120
gpt-5.6-sol	explicit	formal	task_success	-32.9%	-40.0% to -26.2%	120	120	0	120
gpt-5.6-sol	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
gpt-5.6-sol	explicit	implicit	fact_f1	16.8%	12.6% to 21.2%	120	120	0	120
gpt-5.6-sol	explicit	implicit	exact_world	12.9%	5.0% to 20.8%	120	120	0	120
gpt-5.6-sol	explicit	implicit	task_success	12.9%	5.0% to 20.8%	120	120	0	120
gpt-5.6-sol	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
gpt-5.6-sol	formal	implicit	fact_f1	19.6%	15.3% to 23.8%	120	120	0	120
gpt-5.6-sol	formal	implicit	exact_world	45.8%	38.8% to 52.9%	120	120	0	120
gpt-5.6-sol	formal	implicit	task_success	45.8%	38.8% to 52.9%	120	120	0	120
gpt-5.6-sol	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
gpt-5.6-terra	explicit	formal	fact_f1	-3.7%	-4.5% to -3.0%	120	120	0	120
gpt-5.6-terra	explicit	formal	exact_world	-47.5%	-54.2% to -41.2%	120	120	0	120
gpt-5.6-terra	explicit	formal	task_success	-47.5%	-54.2% to -41.2%	120	120	0	120
gpt-5.6-terra	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	120	0	120
gpt-5.6-terra	explicit	implicit	fact_f1	38.1%	32.7% to 43.5%	120	120	0	120
gpt-5.6-terra	explicit	implicit	exact_world	28.3%	20.0% to 36.7%	120	120	0	120
gpt-5.6-terra	explicit	implicit	task_success	28.3%	20.0% to 36.7%	120	120	0	120
gpt-5.6-terra	explicit	implicit	decision_correct	0.4%	0.0% to 1.2%	120	120	0	120
gpt-5.6-terra	formal	implicit	fact_f1	41.9%	36.6% to 47.1%	120	120	0	120
gpt-5.6-terra	formal	implicit	exact_world	75.8%	70.0% to 81.2%	120	120	0	120
gpt-5.6-terra	formal	implicit	task_success	75.8%	70.0% to 81.2%	120	120	0	120
gpt-5.6-terra	formal	implicit	decision_correct	0.4%	0.0% to 1.2%	120	120	0	120
gpt-6-astra	explicit	formal	fact_f1	-0.9%	-1.4% to -0.5%	120	108	12	108
gpt-6-astra	explicit	formal	exact_world	-11.6%	-16.7% to -7.4%	120	108	12	108
gpt-6-astra	explicit	formal	task_success	-11.6%	-16.7% to -7.4%	120	108	12	108
gpt-6-astra	explicit	formal	decision_correct	0.0%	0.0% to 0.0%	120	108	12	108
gpt-6-astra	explicit	implicit	fact_f1	1.3%	0.6% to 2.3%	120	101	19	101
gpt-6-astra	explicit	implicit	exact_world	8.9%	4.5% to 13.9%	120	101	19	101
gpt-6-astra	explicit	implicit	task_success	8.9%	4.5% to 13.9%	120	101	19	101
gpt-6-astra	explicit	implicit	decision_correct	0.0%	0.0% to 0.0%	120	101	19	101
gpt-6-astra	formal	implicit	fact_f1	2.3%	1.4% to 3.3%	120	104	16	104
gpt-6-astra	formal	implicit	exact_world	20.7%	14.4% to 26.9%	120	104	16	104
gpt-6-astra	formal	implicit	task_success	20.7%	14.4% to 26.9%	120	104	16	104
gpt-6-astra	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	104	16	104
gpt-6-luna	explicit	formal	fact_f1	-7.8%	-9.5% to -6.4%	120	120	0	120
gpt-6-luna	explicit	formal	exact_world	-66.7%	-72.1% to -60.8%	120	120	0	120
gpt-6-luna	explicit	formal	task_success	-65.8%	-71.7% to -59.6%	120	120	0	120
gpt-6-luna	explicit	formal	decision_correct	-2.1%	-4.6% to 0.8%	120	120	0	120
gpt-6-luna	explicit	implicit	fact_f1	30.7%	25.1% to 36.4%	120	120	0	120
gpt-6-luna	explicit	implicit	exact_world	10.4%	2.9% to 17.5%	120	120	0	120
gpt-6-luna	explicit	implicit	task_success	10.4%	2.9% to 17.5%	120	120	0	120
gpt-6-luna	explicit	implicit	decision_correct	-2.1%	-4.6% to 0.0%	120	120	0	120
gpt-6-luna	formal	implicit	fact_f1	38.5%	33.1% to 43.9%	120	120	0	120
gpt-6-luna	formal	implicit	exact_world	77.1%	71.2% to 82.5%	120	120	0	120
gpt-6-luna	formal	implicit	task_success	76.2%	69.6% to 82.5%	120	120	0	120
gpt-6-luna	formal	implicit	decision_correct	0.0%	-2.1% to 1.7%	120	120	0	120
gpt-6-sol	explicit	formal	fact_f1	-4.2%	-6.2% to -1.8%	120	120	0	120
gpt-6-sol	explicit	formal	exact_world	-37.9%	-45.0% to -31.2%	120	120	0	120
gpt-6-sol	explicit	formal	task_success	-38.3%	-45.4% to -31.7%	120	120	0	120
gpt-6-sol	explicit	formal	decision_correct	-2.5%	-5.4% to 0.4%	120	120	0	120
gpt-6-sol	explicit	implicit	fact_f1	-2.1%	-3.5% to -0.7%	120	120	0	120
gpt-6-sol	explicit	implicit	exact_world	-13.8%	-20.0% to -7.1%	120	120	0	120
gpt-6-sol	explicit	implicit	task_success	-14.2%	-20.4% to -7.5%	120	120	0	120
gpt-6-sol	explicit	implicit	decision_correct	-3.3%	-5.8% to -1.2%	120	120	0	120
gpt-6-sol	formal	implicit	fact_f1	2.1%	-0.2% to 3.9%	120	120	0	120
gpt-6-sol	formal	implicit	exact_world	24.2%	17.9% to 30.4%	120	120	0	120
gpt-6-sol	formal	implicit	task_success	24.2%	17.9% to 30.4%	120	120	0	120
gpt-6-sol	formal	implicit	decision_correct	-0.8%	-2.5% to 0.0%	120	120	0	120
grok-4.6	explicit	formal	fact_f1	-12.0%	-13.6% to -10.3%	120	120	0	120
grok-4.6	explicit	formal	exact_world	-78.8%	-84.2% to -72.9%	120	120	0	120
grok-4.6	explicit	formal	task_success	-78.8%	-84.2% to -72.9%	120	120	0	120
grok-4.6	explicit	formal	decision_correct	-4.2%	-7.5% to -1.2%	120	120	0	120
grok-4.6	explicit	implicit	fact_f1	2.4%	0.1% to 4.6%	120	120	0	120
grok-4.6	explicit	implicit	exact_world	0.0%	-6.2% to 5.8%	120	120	0	120
grok-4.6	explicit	implicit	task_success	0.0%	-6.2% to 5.8%	120	120	0	120
grok-4.6	explicit	implicit	decision_correct	0.0%	-2.1% to 2.1%	120	120	0	120
grok-4.6	formal	implicit	fact_f1	14.3%	12.2% to 16.4%	120	120	0	120
grok-4.6	formal	implicit	exact_world	78.8%	72.9% to 84.2%	120	120	0	120
grok-4.6	formal	implicit	task_success	78.8%	72.9% to 84.2%	120	120	0	120
grok-4.6	formal	implicit	decision_correct	4.2%	1.7% to 7.1%	120	120	0	120
kimi-k2.6	explicit	formal	fact_f1	-7.6%	-8.6% to -6.5%	120	119	1	119
kimi-k2.6	explicit	formal	exact_world	-76.1%	-81.5% to -70.2%	120	119	1	119
kimi-k2.6	explicit	formal	task_success	-76.1%	-81.5% to -70.2%	120	119	1	119
kimi-k2.6	explicit	formal	decision_correct	-2.1%	-4.2% to -0.4%	120	119	1	119
kimi-k2.6	explicit	implicit	fact_f1	8.2%	5.7% to 10.8%	120	119	1	119
kimi-k2.6	explicit	implicit	exact_world	6.3%	0.0% to 12.6%	120	119	1	119
kimi-k2.6	explicit	implicit	task_success	6.3%	0.0% to 12.6%	120	119	1	119
kimi-k2.6	explicit	implicit	decision_correct	1.3%	-1.3% to 3.8%	120	119	1	119
kimi-k2.6	formal	implicit	fact_f1	16.0%	13.5% to 18.6%	120	120	0	120
kimi-k2.6	formal	implicit	exact_world	82.5%	77.1% to 87.5%	120	120	0	120
kimi-k2.6	formal	implicit	task_success	82.5%	77.1% to 87.5%	120	120	0	120
kimi-k2.6	formal	implicit	decision_correct	3.3%	1.2% to 5.8%	120	120	0	120
kimi-k3	explicit	formal	fact_f1	-15.2%	-18.7% to -11.6%	120	81	39	81
kimi-k3	explicit	formal	exact_world	-73.5%	-80.2% to -66.7%	120	81	39	81
kimi-k3	explicit	formal	task_success	-73.5%	-80.2% to -66.7%	120	81	39	81
kimi-k3	explicit	formal	decision_correct	-0.6%	-1.9% to 0.0%	120	81	39	81
kimi-k3	explicit	implicit	fact_f1	9.1%	4.9% to 13.4%	120	79	41	79
kimi-k3	explicit	implicit	exact_world	2.5%	-5.7% to 11.4%	120	79	41	79
kimi-k3	explicit	implicit	task_success	2.5%	-5.7% to 11.4%	120	79	41	79
kimi-k3	explicit	implicit	decision_correct	-0.6%	-1.9% to 0.0%	120	79	41	79
kimi-k3	formal	implicit	fact_f1	22.7%	17.8% to 27.6%	120	86	34	86
kimi-k3	formal	implicit	exact_world	72.7%	64.5% to 80.2%	120	86	34	86
kimi-k3	formal	implicit	task_success	72.7%	64.5% to 80.2%	120	86	34	86
kimi-k3	formal	implicit	decision_correct	0.0%	0.0% to 0.0%	120	86	34	86
mimo-v2.6-flash	explicit	formal	fact_f1	-6.0%	-10.0% to -1.6%	120	117	3	117
mimo-v2.6-flash	explicit	formal	exact_world	-54.7%	-62.0% to -47.0%	120	117	3	117
mimo-v2.6-flash	explicit	formal	task_success	-53.0%	-60.7% to -44.4%	120	117	3	117
mimo-v2.6-flash	explicit	formal	decision_correct	-2.1%	-7.7% to 3.8%	120	117	3	117
mimo-v2.6-flash	explicit	implicit	fact_f1	30.6%	24.8% to 36.1%	120	115	5	115
mimo-v2.6-flash	explicit	implicit	exact_world	26.5%	19.6% to 33.0%	120	115	5	115
mimo-v2.6-flash	explicit	implicit	task_success	25.7%	18.7% to 32.2%	120	115	5	115
mimo-v2.6-flash	explicit	implicit	decision_correct	4.3%	-0.9% to 10.0%	120	115	5	115
mimo-v2.6-flash	formal	implicit	fact_f1	36.6%	30.8% to 42.0%	120	117	3	117
mimo-v2.6-flash	formal	implicit	exact_world	81.2%	74.8% to 86.8%	120	117	3	117
mimo-v2.6-flash	formal	implicit	task_success	78.6%	71.8% to 85.0%	120	117	3	117
mimo-v2.6-flash	formal	implicit	decision_correct	6.4%	0.0% to 12.8%	120	117	3	117
mimo-v2.6-pro	explicit	formal	fact_f1	-12.8%	-17.1% to -8.0%	120	120	0	120
mimo-v2.6-pro	explicit	formal	exact_world	-55.4%	-62.5% to -47.9%	120	120	0	120
mimo-v2.6-pro	explicit	formal	task_success	-55.8%	-63.3% to -47.9%	120	120	0	120
mimo-v2.6-pro	explicit	formal	decision_correct	-9.2%	-14.6% to -3.3%	120	120	0	120
mimo-v2.6-pro	explicit	implicit	fact_f1	26.3%	20.9% to 31.1%	120	120	0	120
mimo-v2.6-pro	explicit	implicit	exact_world	26.7%	19.6% to 33.8%	120	120	0	120
mimo-v2.6-pro	explicit	implicit	task_success	24.6%	17.5% to 32.1%	120	120	0	120
mimo-v2.6-pro	explicit	implicit	decision_correct	0.0%	-5.8% to 6.2%	120	120	0	120
mimo-v2.6-pro	formal	implicit	fact_f1	39.1%	34.4% to 43.6%	120	120	0	120
mimo-v2.6-pro	formal	implicit	exact_world	82.1%	75.8% to 87.9%	120	120	0	120
mimo-v2.6-pro	formal	implicit	task_success	80.4%	73.8% to 86.7%	120	120	0	120
mimo-v2.6-pro	formal	implicit	decision_correct	9.2%	3.3% to 15.0%	120	120	0	120
minimax-m3	explicit	formal	fact_f1	-28.0%	-33.7% to -22.7%	120	120	0	120
minimax-m3	explicit	formal	exact_world	-72.9%	-79.6% to -66.2%	120	120	0	120
minimax-m3	explicit	formal	task_success	-72.9%	-79.6% to -66.2%	120	120	0	120
minimax-m3	explicit	formal	decision_correct	-0.8%	-4.6% to 2.9%	120	120	0	120
minimax-m3	explicit	implicit	fact_f1	16.6%	9.9% to 23.2%	120	120	0	120
minimax-m3	explicit	implicit	exact_world	13.3%	6.2% to 20.8%	120	120	0	120
minimax-m3	explicit	implicit	task_success	13.3%	6.2% to 20.8%	120	120	0	120
minimax-m3	explicit	implicit	decision_correct	0.4%	-2.5% to 3.3%	120	120	0	120
minimax-m3	formal	implicit	fact_f1	44.6%	38.5% to 50.6%	120	120	0	120
minimax-m3	formal	implicit	exact_world	86.2%	80.8% to 91.2%	120	120	0	120
minimax-m3	formal	implicit	task_success	86.2%	80.8% to 91.2%	120	120	0	120
minimax-m3	formal	implicit	decision_correct	1.2%	-2.5% to 4.6%	120	120	0	120
qwen3.8-27b	explicit	formal	fact_f1	-9.3%	-13.8% to -4.3%	120	120	0	120
qwen3.8-27b	explicit	formal	exact_world	-71.7%	-78.8% to -64.6%	120	120	0	120
qwen3.8-27b	explicit	formal	task_success	-71.7%	-78.8% to -64.6%	120	120	0	120
qwen3.8-27b	explicit	formal	decision_correct	1.2%	-2.9% to 5.8%	120	120	0	120
qwen3.8-27b	explicit	implicit	fact_f1	11.9%	7.9% to 15.9%	120	120	0	120
qwen3.8-27b	explicit	implicit	exact_world	12.1%	5.8% to 18.3%	120	120	0	120
qwen3.8-27b	explicit	implicit	task_success	12.1%	5.8% to 18.3%	120	120	0	120
qwen3.8-27b	explicit	implicit	decision_correct	-0.4%	-2.5% to 1.2%	120	120	0	120
qwen3.8-27b	formal	implicit	fact_f1	21.2%	15.7% to 26.2%	120	120	0	120
qwen3.8-27b	formal	implicit	exact_world	83.8%	77.9% to 89.2%	120	120	0	120
qwen3.8-27b	formal	implicit	task_success	83.8%	77.9% to 89.2%	120	120	0	120
qwen3.8-27b	formal	implicit	decision_correct	-1.7%	-6.2% to 2.5%	120	120	0	120

Structural depth by configured level

{
  "by_family": {
    "inst-strata-L00-000-theater": {
      "constraint_kinds": {
        "eq": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.875,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-001-maritime": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-002-hotel": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-003-manor": {
      "constraint_kinds": {
        "eq": 5,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-004-manor": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-005-theater": {
      "constraint_kinds": {
        "eq": 4,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-006-theater": {
      "constraint_kinds": {
        "eq": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.875,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-007-hotel": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 1
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.875,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-008-maritime": {
      "constraint_kinds": {
        "eq": 5,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-009-maritime": {
      "constraint_kinds": {
        "eq": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 1.0,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 0,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-010-theater": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 1
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-011-hotel": {
      "constraint_kinds": {
        "eq": 4,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-012-manor": {
      "constraint_kinds": {
        "eq": 5,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 2,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 2,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-013-hotel": {
      "constraint_kinds": {
        "eq": 5,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-014-theater": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 1,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 2
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 2,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-015-maritime": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-016-maritime": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 1
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 2,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-017-manor": {
      "constraint_kinds": {
        "eq": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-018-theater": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L00-019-theater": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 1
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0
      },
      "direct_assignment_fraction": 0.875,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 8,
      "forward_chain_rounds": 1,
      "n_constraints": 8,
      "n_variables": 8,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-000-hotel": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 1,
        "neq": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V11": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V8": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 9,
      "forward_chain_complete": false,
      "forward_chain_fraction": 0.75,
      "forward_chain_recovered": 9,
      "forward_chain_rounds": 0,
      "n_constraints": 15,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": [
        "V7",
        "V9",
        "V10"
      ]
    },
    "inst-strata-L01-001-manor": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 2,
        "V11": 3,
        "V2": 1,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 3,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-002-observatory": {
      "constraint_kinds": {
        "eq": 8,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 2,
        "V2": 1,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-003-observatory": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 1,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-004-observatory": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 2,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 6,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-005-maritime": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 1,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-006-theater": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-007-hotel": {
      "constraint_kinds": {
        "eq": 8,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 0,
        "V2": 1,
        "V3": 0,
        "V4": 1,
        "V5": 2,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-008-manor": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 1,
        "V2": 0,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 1,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-009-theater": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 2,
        "V11": 3,
        "V2": 3,
        "V3": 2,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 2,
        "V8": 3,
        "V9": 0
      },
      "direct_assignment_fraction": 0.25,
      "direct_assignments": 3,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 3,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-010-manor": {
      "constraint_kinds": {
        "eq": 6,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 2,
        "V9": 1
      },
      "direct_assignment_fraction": 0.3333333333333333,
      "direct_assignments": 4,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-011-theater": {
      "constraint_kinds": {
        "eq": 8,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-012-manor": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.8333333333333334,
      "direct_assignments": 10,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 1,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-013-observatory": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 2,
        "V11": 3,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 3,
        "V6": 0,
        "V7": 0,
        "V8": 3,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 3,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-014-theater": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-015-manor": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 1,
        "V11": 0,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 2,
        "V6": 1,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.4166666666666667,
      "direct_assignments": 5,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-016-maritime": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V2": 1,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 1,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-017-observatory": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-018-manor": {
      "constraint_kinds": {
        "eq": 8,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L01-019-theater": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 1,
        "V11": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 12,
      "forward_chain_rounds": 2,
      "n_constraints": 12,
      "n_variables": 12,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-000-observatory": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-001-hotel": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V2": 3,
        "V3": 0,
        "V4": 1,
        "V5": 2,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 3,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-002-maritime": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-003-hotel": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 10,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-004-hotel": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-005-theater": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 2,
        "V6": 0,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.4375,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-006-observatory": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.8125,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-007-observatory": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V2": 2,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-008-hotel": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5625,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-009-observatory": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 2,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-010-observatory": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 1,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-011-observatory": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 2,
        "V11": 1,
        "V12": 1,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 12,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-012-theater": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-013-manor": {
      "constraint_kinds": {
        "eq": 7,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 2,
        "V6": 0,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.4375,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-014-hotel": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 3
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-015-theater": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-016-hotel": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 12,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-017-theater": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6875,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 2,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-018-manor": {
      "constraint_kinds": {
        "eq": 15,
        "implies": 1
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.8125,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 1,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L02-019-maritime": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 2,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 1,
        "V2": 2,
        "V3": 0,
        "V4": 2,
        "V5": 3,
        "V6": 0,
        "V7": 0,
        "V8": 3,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 16,
      "forward_chain_rounds": 3,
      "n_constraints": 16,
      "n_variables": 16,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-000-maritime": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 0,
        "V2": 1,
        "V3": 3,
        "V4": 0,
        "V5": 0,
        "V6": 2,
        "V7": 1,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.55,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-001-theater": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 11
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 2,
        "V11": 3,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 3,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 3,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.4,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-002-hotel": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 2
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 1,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 1,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-003-theater": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 2,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 0,
        "V2": 2,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 3,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6,
      "direct_assignments": 12,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-004-maritime": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 4,
        "V12": 0,
        "V13": 0,
        "V14": 3,
        "V15": 0,
        "V16": 0,
        "V17": 2,
        "V18": 2,
        "V19": 0,
        "V2": 2,
        "V3": 0,
        "V4": 1,
        "V5": 1,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.65,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 4,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-005-hotel": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 1,
        "V15": 2,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 2,
        "V2": 1,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 2,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.45,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 2,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-006-observatory": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 0,
        "V11": 4,
        "V12": 1,
        "V13": 2,
        "V14": 3,
        "V15": 1,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 2,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6,
      "direct_assignments": 12,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 4,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-007-observatory": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 1,
        "V11": 3,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 3,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 3,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.45,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-008-theater": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 1,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 2,
        "V18": 1,
        "V19": 1,
        "V2": 0,
        "V3": 2,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.65,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 2,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-009-observatory": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 4,
        "V12": 0,
        "V13": 2,
        "V14": 3,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 0,
        "V2": 3,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.55,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 4,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-010-observatory": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 3,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 0,
        "V2": 1,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 2,
        "V7": 3,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.45,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-011-manor": {
      "constraint_kinds": {
        "eq": 15,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 1,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 1,
        "V2": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 1,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-012-theater": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 1,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 1,
        "V2": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.7,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 1,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-013-hotel": {
      "constraint_kinds": {
        "eq": 15,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 2,
        "V16": 0,
        "V17": 2,
        "V18": 0,
        "V19": 4,
        "V2": 0,
        "V3": 1,
        "V4": 1,
        "V5": 0,
        "V6": 3,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.55,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 4,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-014-hotel": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 0,
        "V2": 0,
        "V3": 3,
        "V4": 1,
        "V5": 2,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.55,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-015-manor": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 3,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 2,
        "V2": 1,
        "V3": 3,
        "V4": 0,
        "V5": 0,
        "V6": 2,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 10,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-016-theater": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 1,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 10,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 1,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-017-theater": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 0,
        "V2": 2,
        "V3": 3,
        "V4": 0,
        "V5": 1,
        "V6": 1,
        "V7": 3,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.55,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-018-theater": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 2,
        "V11": 3,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 3,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 0,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 2,
        "V7": 1,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.45,
      "direct_assignments": 9,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 3,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L03-019-observatory": {
      "constraint_kinds": {
        "eq": 11,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V10": 1,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 2,
        "V2": 2,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 10,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 20,
      "forward_chain_rounds": 2,
      "n_constraints": 20,
      "n_variables": 20,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-000-observatory": {
      "constraint_kinds": {
        "eq": 19,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 2,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 1,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 2,
        "V7": 0,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-001-theater": {
      "constraint_kinds": {
        "eq": 9,
        "implies": 15
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 2,
        "V11": 3,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 3,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 3,
        "V3": 3,
        "V4": 0,
        "V5": 1,
        "V6": 2,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.2916666666666667,
      "direct_assignments": 7,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-002-manor": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 1,
        "V13": 0,
        "V14": 0,
        "V15": 2,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 0,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 1,
        "V3": 3,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-003-hotel": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 3,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 1,
        "V2": 0,
        "V20": 0,
        "V21": 0,
        "V22": 2,
        "V23": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5416666666666666,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-004-maritime": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 1,
        "V3": 1,
        "V4": 1,
        "V5": 1,
        "V6": 1,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-005-hotel": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 10,
        "neq": 4
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 1,
        "V11": 0,
        "V13": 1,
        "V14": 1,
        "V15": 2,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 1,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 1,
        "V3": 2,
        "V4": 0,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.4583333333333333,
      "direct_assignments": 11,
      "forward_chain_complete": false,
      "forward_chain_fraction": 0.9166666666666666,
      "forward_chain_recovered": 22,
      "forward_chain_rounds": 2,
      "n_constraints": 27,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": [
        "V5",
        "V12"
      ]
    },
    "inst-strata-L04-006-hotel": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 2,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 2,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 2,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 1,
        "V23": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 1,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-007-manor": {
      "constraint_kinds": {
        "eq": 19,
        "implies": 5
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 1,
        "V23": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.75,
      "direct_assignments": 18,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-008-observatory": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 12
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 1,
        "V12": 1,
        "V13": 2,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 2,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 1,
        "V3": 3,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 3,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.4583333333333333,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-009-maritime": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 2,
        "V15": 3,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 0,
        "V22": 2,
        "V23": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 3,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-010-observatory": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 2,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 1,
        "V2": 2,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 1,
        "V3": 1,
        "V4": 1,
        "V5": 0,
        "V6": 2,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5416666666666666,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-011-observatory": {
      "constraint_kinds": {
        "eq": 17,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 2,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 1,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 2,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 0,
        "V3": 3,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-012-theater": {
      "constraint_kinds": {
        "eq": 17,
        "implies": 7
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 2,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.625,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-013-theater": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 2,
        "V22": 1,
        "V23": 0,
        "V3": 2,
        "V4": 1,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-014-manor": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 1,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 0,
        "V3": 3,
        "V4": 0,
        "V5": 0,
        "V6": 2,
        "V7": 3,
        "V8": 1,
        "V9": 1
      },
      "direct_assignment_fraction": 0.4583333333333333,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-015-observatory": {
      "constraint_kinds": {
        "eq": 15,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 0,
        "V15": 3,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 0,
        "V2": 2,
        "V20": 0,
        "V21": 0,
        "V22": 2,
        "V23": 3,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 2,
        "V8": 1,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5833333333333334,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-016-observatory": {
      "constraint_kinds": {
        "eq": 13,
        "implies": 11
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 2,
        "V10": 1,
        "V11": 0,
        "V12": 0,
        "V13": 1,
        "V14": 3,
        "V15": 0,
        "V16": 1,
        "V17": 0,
        "V18": 3,
        "V19": 1,
        "V2": 0,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 1,
        "V3": 2,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 4,
        "V8": 0,
        "V9": 2
      },
      "direct_assignment_fraction": 0.4583333333333333,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 4,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-017-observatory": {
      "constraint_kinds": {
        "eq": 20,
        "implies": 4
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 3,
        "V11": 2,
        "V12": 0,
        "V13": 2,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6666666666666666,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 3,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-018-hotel": {
      "constraint_kinds": {
        "eq": 12,
        "implies": 12
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 1,
        "V14": 0,
        "V15": 1,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 1,
        "V3": 1,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 2,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.4583333333333333,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L04-019-maritime": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 2,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 0,
        "V3": 1,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 2,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.7083333333333334,
      "direct_assignments": 17,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 24,
      "forward_chain_rounds": 2,
      "n_constraints": 24,
      "n_variables": 24,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-000-theater": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 14
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 2,
        "V12": 2,
        "V13": 0,
        "V14": 1,
        "V15": 3,
        "V16": 1,
        "V17": 2,
        "V18": 0,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 2,
        "V23": 0,
        "V24": 1,
        "V25": 0,
        "V26": 1,
        "V27": 1,
        "V3": 3,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 1,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.39285714285714285,
      "direct_assignments": 11,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-001-maritime": {
      "constraint_kinds": {
        "eq": 17,
        "implies": 11
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 2,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 1,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 2,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 0,
        "V3": 0,
        "V4": 3,
        "V5": 0,
        "V6": 1,
        "V7": 2,
        "V8": 1,
        "V9": 2
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-002-maritime": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 12
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 2,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 1,
        "V19": 3,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 2,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-003-manor": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 2,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V16": 1,
        "V17": 0,
        "V18": 0,
        "V19": 1,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 1,
        "V24": 1,
        "V25": 0,
        "V26": 1,
        "V27": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 2,
        "V8": 3,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-004-maritime": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 1,
        "V17": 2,
        "V18": 0,
        "V19": 1,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 3,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 1,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-005-theater": {
      "constraint_kinds": {
        "eq": 19,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 1,
        "V11": 2,
        "V12": 1,
        "V13": 4,
        "V14": 5,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 1,
        "V19": 0,
        "V2": 3,
        "V20": 0,
        "V21": 0,
        "V22": 3,
        "V23": 4,
        "V24": 2,
        "V25": 0,
        "V26": 0,
        "V27": 0,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 1,
        "V8": 4,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 5,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-006-hotel": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V12": 2,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V16": 1,
        "V17": 0,
        "V18": 0,
        "V19": 2,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 1,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.6071428571428571,
      "direct_assignments": 17,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 2,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-007-manor": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 1,
        "V13": 0,
        "V14": 2,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 0,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 2,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6428571428571429,
      "direct_assignments": 18,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 2,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-008-theater": {
      "constraint_kinds": {
        "eq": 20,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 1,
        "V13": 4,
        "V14": 0,
        "V15": 0,
        "V16": 2,
        "V17": 0,
        "V18": 0,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 2,
        "V22": 0,
        "V23": 1,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 3,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 0,
        "V9": 0
      },
      "direct_assignment_fraction": 0.6071428571428571,
      "direct_assignments": 17,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 4,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-009-theater": {
      "constraint_kinds": {
        "eq": 15,
        "implies": 13
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 2,
        "V12": 1,
        "V13": 0,
        "V14": 3,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 2,
        "V19": 0,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 3,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 3,
        "V3": 2,
        "V4": 1,
        "V5": 1,
        "V6": 1,
        "V7": 1,
        "V8": 2,
        "V9": 0
      },
      "direct_assignment_fraction": 0.42857142857142855,
      "direct_assignments": 12,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-010-theater": {
      "constraint_kinds": {
        "eq": 19,
        "implies": 9
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V12": 1,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 3,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 2,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 1,
        "V3": 0,
        "V4": 0,
        "V5": 2,
        "V6": 1,
        "V7": 2,
        "V8": 0,
        "V9": 3
      },
      "direct_assignment_fraction": 0.5357142857142857,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-011-hotel": {
      "constraint_kinds": {
        "eq": 17,
        "implies": 11
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 1,
        "V12": 1,
        "V13": 1,
        "V14": 3,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 1,
        "V23": 2,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 0,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 1,
        "V8": 1,
        "V9": 2
      },
      "direct_assignment_fraction": 0.5357142857142857,
      "direct_assignments": 15,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-012-observatory": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 12
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 0,
        "V14": 3,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 1,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 1,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 1,
        "V9": 2
      },
      "direct_assignment_fraction": 0.5,
      "direct_assignments": 14,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-013-observatory": {
      "constraint_kinds": {
        "eq": 22,
        "implies": 6
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 0,
        "V13": 2,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 1,
        "V18": 0,
        "V19": 2,
        "V2": 0,
        "V20": 0,
        "V21": 1,
        "V22": 0,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 1,
        "V3": 1,
        "V4": 0,
        "V5": 0,
        "V6": 1,
        "V7": 0,
        "V8": 0,
        "V9": 1
      },
      "direct_assignment_fraction": 0.7142857142857143,
      "direct_assignments": 20,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 2,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-014-theater": {
      "constraint_kinds": {
        "eq": 20,
        "implies": 8
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 1,
        "V12": 1,
        "V13": 2,
        "V14": 0,
        "V15": 0,
        "V16": 2,
        "V17": 1,
        "V18": 1,
        "V19": 0,
        "V2": 0,
        "V20": 0,
        "V21": 0,
        "V22": 1,
        "V23": 0,
        "V24": 1,
        "V25": 0,
        "V26": 0,
        "V27": 0,
        "V3": 0,
        "V4": 0,
        "V5": 0,
        "V6": 0,
        "V7": 1,
        "V8": 1,
        "V9": 0
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 2,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-015-maritime": {
      "constraint_kinds": {
        "eq": 16,
        "implies": 12
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 0,
        "V12": 2,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 0,
        "V17": 2,
        "V18": 2,
        "V19": 3,
        "V2": 1,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 2,
        "V24": 1,
        "V25": 0,
        "V26": 1,
        "V27": 0,
        "V3": 0,
        "V4": 0,
        "V5": 1,
        "V6": 0,
        "V7": 1,
        "V8": 0,
        "V9": 3
      },
      "direct_assignment_fraction": 0.4642857142857143,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-016-manor": {
      "constraint_kinds": {
        "eq": 18,
        "implies": 10
      },
      "derivation_rounds": {
        "V0": 1,
        "V1": 0,
        "V10": 0,
        "V11": 0,
        "V12": 2,
        "V13": 0,
        "V14": 1,
        "V15": 0,
        "V16": 2,
        "V17": 0,
        "V18": 2,
        "V19": 3,
        "V2": 1,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 2,
        "V3": 0,
        "V4": 1,
        "V5": 0,
        "V6": 0,
        "V7": 0,
        "V8": 3,
        "V9": 1
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 3,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-017-theater": {
      "constraint_kinds": {
        "eq": 17,
        "implies": 11
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 2,
        "V13": 1,
        "V14": 0,
        "V15": 0,
        "V16": 1,
        "V17": 0,
        "V18": 0,
        "V19": 2,
        "V2": 2,
        "V20": 0,
        "V21": 0,
        "V22": 0,
        "V23": 0,
        "V24": 0,
        "V25": 0,
        "V26": 0,
        "V27": 0,
        "V3": 0,
        "V4": 2,
        "V5": 0,
        "V6": 1,
        "V7": 1,
        "V8": 1,
        "V9": 2
      },
      "direct_assignment_fraction": 0.5714285714285714,
      "direct_assignments": 16,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 2,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-018-manor": {
      "constraint_kinds": {
        "eq": 10,
        "implies": 18
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 1,
        "V11": 1,
        "V12": 2,
        "V13": 3,
        "V14": 4,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 2,
        "V19": 3,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 2,
        "V24": 4,
        "V25": 1,
        "V26": 1,
        "V27": 1,
        "V3": 0,
        "V4": 3,
        "V5": 0,
        "V6": 0,
        "V7": 2,
        "V8": 3,
        "V9": 3
      },
      "direct_assignment_fraction": 0.2857142857142857,
      "direct_assignments": 8,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 4,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    },
    "inst-strata-L05-019-theater": {
      "constraint_kinds": {
        "eq": 14,
        "implies": 14
      },
      "derivation_rounds": {
        "V0": 0,
        "V1": 1,
        "V10": 0,
        "V11": 1,
        "V12": 0,
        "V13": 3,
        "V14": 0,
        "V15": 0,
        "V16": 0,
        "V17": 0,
        "V18": 0,
        "V19": 4,
        "V2": 2,
        "V20": 0,
        "V21": 1,
        "V22": 2,
        "V23": 1,
        "V24": 0,
        "V25": 0,
        "V26": 1,
        "V27": 2,
        "V3": 3,
        "V4": 1,
        "V5": 0,
        "V6": 1,
        "V7": 2,
        "V8": 0,
        "V9": 4
      },
      "direct_assignment_fraction": 0.4642857142857143,
      "direct_assignments": 13,
      "forward_chain_complete": true,
      "forward_chain_fraction": 1.0,
      "forward_chain_recovered": 28,
      "forward_chain_rounds": 4,
      "n_constraints": 28,
      "n_variables": 28,
      "note": "Depth measures this propagator, not minimum proof length or intrinsic difficulty.",
      "unresolved_by_forward_chain": []
    }
  },
  "families_measured": 120,
  "numeric_summary": {
    "direct_assignment_fraction": {
      "max": 1.0,
      "mean": 0.5939831349206349,
      "min": 0.25,
      "n": 120
    },
    "direct_assignments": {
      "max": 20,
      "mean": 10.383333333333333,
      "min": 3,
      "n": 120
    },
    "forward_chain_fraction": {
      "max": 1.0,
      "mean": 0.9972222222222222,
      "min": 0.75,
      "n": 120
    },
    "forward_chain_recovered": {
      "max": 28,
      "mean": 17.958333333333332,
      "min": 8,
      "n": 120
    },
    "forward_chain_rounds": {
      "max": 5,
      "mean": 2.158333333333333,
      "min": 0,
      "n": 120
    },
    "n_constraints": {
      "max": 28,
      "mean": 18.05,
      "min": 8,
      "n": 120
    },
    "n_variables": {
      "max": 28,
      "mean": 18.0,
      "min": 8,
      "n": 120
    }
  }
}

The full solver inputs (all realizations), hidden fact patterns, and per-record details are large, so they live in a companion file that loads separately:

Open stories & raw records

The companion file contains every solver input, the hidden fact pattern per world, decision policies with measured difficulty, and the full per-record JSON for all providers.

Earned decisions (/100) — correct actions on an exactly-right world

Configured level: 0
Instance	Provider	Status	Correct	Submitted action
inst-strata-L00-000-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L00-000-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-000-theater--explicit-r1	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L00-000-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "costume plot", "value": "1" }
inst-strata-L00-000-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-000-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-000-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-000-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-000-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-000-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-000-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-000-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-000-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "costume plot", "value": "1" }
inst-strata-L00-000-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-000-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-000-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "costume plot", "value": "1" }
inst-strata-L00-000-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-000-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": 1 }
inst-strata-L00-000-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-001-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-001-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L00-001-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-001-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-001-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-001-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-001-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-001-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-001-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-001-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-001-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-001-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-001-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-001-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	claude-opus-5.5	answered	0.0%	null
inst-strata-L00-001-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-001-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-001-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-001-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	glm-5.3	answered	0.0%	{ "operation": "hold", "subject": "watch rotation", "value": "3" }
inst-strata-L00-001-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-001-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 3 }
inst-strata-L00-001-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-001-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-001-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-002-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-002-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-002-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-002-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-002-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-6-sol	answered	0.0%	{ "operation": "register", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "bar ledger", "value": "1" }
inst-strata-L00-002-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-002-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-002-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-002-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L00-002-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-002-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-002-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-002-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-002-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-002-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-002-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L00-002-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-002-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-002-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-002-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "bar ledger", "value": "1" }
inst-strata-L00-002-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "bar ledger", "value": 1 }
inst-strata-L00-002-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-002-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-002-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-003-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L00-003-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-003-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-003-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L00-003-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-003-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-003-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L00-003-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-003-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-003-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-003-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-003-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-003-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-003-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-003-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L00-003-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-003-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Juno" }
inst-strata-L00-003-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-004-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-004-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-004-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-004-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	mimo-v2.6-flash	transport_error	—	null
inst-strata-L00-004-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-004-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-004-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-004-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-004-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-004-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-004-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-004-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-004-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-004-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-004-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-004-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-004-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L00-004-manor--implicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": "3" }
inst-strata-L00-004-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "seed ledger", "value": 3 }
inst-strata-L00-004-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-004-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-004-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-005-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	mimo-v2.6-flash	transport_error	—	null
inst-strata-L00-005-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-005-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-005-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-005-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-005-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-005-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-005-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-005-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-005-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-005-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-005-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-005-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	mimo-v2.6-flash	transport_error	—	null
inst-strata-L00-005-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-005-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-005-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-005-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L00-005-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L00-005-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-005-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-005-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-006-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-006-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-006-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-006-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-006-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": "signed out under Galia" }
inst-strata-L00-006-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-006-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-006-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-006-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-006-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-006-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia's mark" }
inst-strata-L00-006-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": "carried Galia's mark" }
inst-strata-L00-006-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-006-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-006-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-006-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": "signed out under Galia" }
inst-strata-L00-006-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-006-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "understudy roster", "value": "Galia" }
inst-strata-L00-006-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-007-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-007-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-007-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-007-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--explicit-r2	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-007-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-007-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-007-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-007-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L00-007-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-007-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-007-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-007-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-007-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-007-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L00-007-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-007-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-007-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-007-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lift log", "value": "Iris" }
inst-strata-L00-007-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-007-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-007-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-008-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-008-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-008-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-008-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	minimax-m3	invalid_response	0.0%	null
inst-strata-L00-008-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-008-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-008-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-008-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-008-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-008-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-008-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-008-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-008-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-008-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-008-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-008-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-008-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	claude-fable-5.1	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": "Roan" }
inst-strata-L00-008-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-008-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-009-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-009-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	glm-5.3-flash	transport_error	—	null
inst-strata-L00-009-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-009-maritime--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-009-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L00-009-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro's mark" }
inst-strata-L00-009-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-009-maritime--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-009-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-009-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-009-maritime--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-009-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-009-maritime--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-009-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro's mark" }
inst-strata-L00-009-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-009-maritime--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Ferro" }
inst-strata-L00-009-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-010-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-010-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-010-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-010-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L00-010-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-010-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-010-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-010-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-010-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L00-010-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-010-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-010-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-010-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L00-010-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-010-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-010-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-010-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "call sheet", "value": "Ansel" }
inst-strata-L00-010-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-010-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-010-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-011-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L00-011-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-011-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-011-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-011-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L00-011-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-011-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-011-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-011-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L00-011-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-011-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-011-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-011-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-011-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-011-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-011-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-011-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-011-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L00-011-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 2 }
inst-strata-L00-011-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-011-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-011-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-012-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L00-012-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "mill ledger", "value": "4" }
inst-strata-L00-012-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-012-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-012-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-012-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-012-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L00-012-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-012-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-012-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-012-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-012-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-012-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-012-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-012-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-012-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L00-012-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-012-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-012-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-012-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "register", "subject": "mill ledger", "value": 2 }
inst-strata-L00-012-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-012-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mill ledger", "value": 4 }
inst-strata-L00-012-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-012-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-012-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-013-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-013-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-013-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-013-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-013-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-013-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-013-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L00-013-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-013-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-013-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-013-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-013-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-013-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-013-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-013-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	mimo-v2.6-flash	transport_error	—	null
inst-strata-L00-013-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "bar ledger", "value": "Galia" }
inst-strata-L00-013-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-013-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-013-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-014-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-014-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L00-014-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-014-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-014-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-014-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-014-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L00-014-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-014-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-014-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-014-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-014-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-014-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-014-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-014-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-014-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-014-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-014-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-014-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": "Cassia" }
inst-strata-L00-014-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-014-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-014-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-015-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-015-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-015-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-015-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L00-015-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-015-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-015-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-015-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-015-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-015-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-015-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-015-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-015-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L00-015-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-015-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	mimo-v2.6-flash	transport_error	—	null
inst-strata-L00-015-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L00-015-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "broker's stamp", "value": "1" }
inst-strata-L00-015-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-015-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-015-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-015-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	glm-5.3	answered	0.0%	{ "operation": "hold", "subject": "broker's stamp", "value": "1" }
inst-strata-L00-015-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L00-015-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-015-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "broker's stamp", "value": "1" }
inst-strata-L00-015-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "broker's stamp", "value": 1 }
inst-strata-L00-015-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-015-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-015-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-016-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-016-maritime--explicit-r1	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L00-016-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-016-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-016-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-016-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-6-sol	answered	0.0%	{ "operation": "hold", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-016-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-016-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-016-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-016-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-016-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-016-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-016-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-016-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "crate mark", "value": "3" }
inst-strata-L00-016-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L00-016-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "crate mark", "value": "3" }
inst-strata-L00-016-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-016-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-016-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-016-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "crate mark", "value": 3 }
inst-strata-L00-016-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-016-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-016-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-017-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gemini-3.8-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-sonnet-5	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	minimax-m3	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": "4" }
inst-strata-L00-017-manor--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-017-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-017-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-017-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-6-sol	invalid_response	0.0%	null
inst-strata-L00-017-manor--explicit-r2	gemini-3.7-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	glm-5.3	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gemini-3.6-flash	invalid_response	0.0%	null
inst-strata-L00-017-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-6-luna	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L00-017-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-017-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L00-017-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-017-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-017-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-017-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-017-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-017-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-017-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-017-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-017-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-017-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-017-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	grok-4.6	answered	0.0%	null
inst-strata-L00-017-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tenant roll", "value": 4 }
inst-strata-L00-017-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-017-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-017-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-018-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin's mark" }
inst-strata-L00-018-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin's mark" }
inst-strata-L00-018-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-018-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-018-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-018-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin's mark" }
inst-strata-L00-018-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-018-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-018-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-018-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-018-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-018-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-018-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-018-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin's mark" }
inst-strata-L00-018-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L00-018-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin's mark" }
inst-strata-L00-018-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-018-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-018-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-018-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L00-018-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L00-018-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": "Corin" }
inst-strata-L00-018-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-018-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-018-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-019-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L00-019-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-019-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-019-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-019-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--explicit-r2	glm-4.7-flash	answered	0.0%	null
inst-strata-L00-019-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-019-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-019-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-019-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L00-019-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L00-019-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-019-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-019-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L00-019-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L00-019-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-019-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L00-019-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "call sheet", "value": "Wren" }
inst-strata-L00-019-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 2 }
inst-strata-L00-019-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "call sheet", "value": "2" }
inst-strata-L00-019-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L00-019-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L00-019-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Configured level: 1
Instance	Provider	Status	Correct	Submitted action
inst-strata-L01-000-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L01-000-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L01-000-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L01-000-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-000-hotel--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-000-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-000-hotel--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-000-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L01-000-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-000-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-000-hotel--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-000-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-000-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-000-hotel--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-000-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-000-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-000-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-000-hotel--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "patrol book", "value": "Silas" }
inst-strata-L01-000-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-001-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L01-001-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-001-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-001-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-001-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L01-001-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-001-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-001-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-001-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-001-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-001-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-001-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-001-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-001-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L01-001-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-001-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L01-001-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-001-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-001-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-001-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L01-001-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-001-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-001-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Lyra" }
inst-strata-L01-001-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-001-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-001-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-002-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-002-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-002-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-002-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-002-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-002-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-002-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-002-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-002-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-002-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-002-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-002-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-002-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-002-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-002-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-002-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-002-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": "Petra" }
inst-strata-L01-002-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-002-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-002-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-003-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L01-003-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L01-003-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-003-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-003-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-003-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-6-sol	answered	0.0%	null
inst-strata-L01-003-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L01-003-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L01-003-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-003-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-003-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-003-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-003-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-003-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-003-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-003-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-003-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-003-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-003-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-003-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-003-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-003-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L01-003-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	minimax-m3	invalid_response	0.0%	null
inst-strata-L01-003-observatory--implicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L01-003-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": "Wren" }
inst-strata-L01-003-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-003-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-003-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-004-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-004-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-004-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-004-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-sonnet-5	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-opus-5	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	qwen3.8-27b	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-004-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-004-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-004-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-004-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-004-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-004-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-004-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	claude-opus-5.5	content_filter	—	null
inst-strata-L01-004-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "snow-cat log", "value": "2" }
inst-strata-L01-004-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-004-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-004-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-004-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	qwen3.8-27b	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "snow-cat log", "value": 2 }
inst-strata-L01-004-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-004-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-004-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-005-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-005-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-005-maritime--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-005-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-005-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-005-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L01-005-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-005-maritime--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-005-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-005-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-005-maritime--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-005-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-005-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-005-maritime--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-005-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-005-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-005-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-005-maritime--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": 3 }
inst-strata-L01-005-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-006-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-006-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L01-006-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-006-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-006-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-006-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-006-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-006-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-006-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-006-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-006-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-006-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-006-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-006-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-006-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-006-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-006-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prompt book", "value": "Halden" }
inst-strata-L01-006-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-006-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-006-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-007-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-007-hotel--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-007-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-007-hotel--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-007-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L01-007-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-007-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-007-hotel--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-007-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-007-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	glm-5.3-flash	answered	0.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "3" }
inst-strata-L01-007-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-007-hotel--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-007-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L01-007-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "3" }
inst-strata-L01-007-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-007-hotel--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": 3 }
inst-strata-L01-007-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-008-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-008-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-008-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-008-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-008-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-008-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-008-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-008-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L01-008-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-008-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-008-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-008-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-008-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-008-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-008-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-008-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r2	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "seed ledger", "value": 4 }
inst-strata-L01-008-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-008-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-008-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Sable" }
inst-strata-L01-008-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-009-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L01-009-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	claude-opus-5.5	answered	0.0%	{ "operation": "register", "subject": "costume plot", "value": "2" }
inst-strata-L01-009-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-009-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-009-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-009-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-009-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L01-009-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	glm-5.3-flash	transport_error	—	null
inst-strata-L01-009-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "costume plot", "value": "2" }
inst-strata-L01-009-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-009-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-009-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-009-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-009-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-009-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-009-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-009-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-009-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "costume plot", "value": "2" }
inst-strata-L01-009-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-009-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-009-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-009-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-009-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-009-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "costume plot", "value": 2 }
inst-strata-L01-009-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "costume plot", "value": "2" }
inst-strata-L01-009-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-009-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-009-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-010-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-010-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-010-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-010-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L01-010-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-010-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-010-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-010-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-010-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-010-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-010-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-010-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-010-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-010-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L01-010-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "parish register", "value": "1" }
inst-strata-L01-010-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-010-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "parish register", "value": 1 }
inst-strata-L01-010-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-011-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-011-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-011-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-011-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-011-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-011-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-011-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-011-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-011-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-011-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-011-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-011-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-011-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-011-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-011-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-011-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-011-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-011-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-011-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "costume plot", "value": "Silas" }
inst-strata-L01-011-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-011-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-011-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-012-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-012-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-012-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-012-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-012-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-012-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-012-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-012-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-012-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-012-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas's mark" }
inst-strata-L01-012-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-012-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-012-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-012-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-012-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "Silas" }
inst-strata-L01-012-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-013-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L01-013-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-013-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-013-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-013-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-013-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-013-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-013-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-013-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-013-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-013-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-013-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L01-013-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-013-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-013-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L01-013-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-013-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 1 }
inst-strata-L01-013-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-014-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-014-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-014-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-014-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-014-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-014-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-014-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-014-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-014-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-014-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-014-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L01-014-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-014-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-014-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-014-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "stage manager's log", "value": "3" }
inst-strata-L01-014-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L01-014-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "stage manager's log", "value": "3" }
inst-strata-L01-014-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-014-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L01-014-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-015-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	glm-5.3	invalid_response	0.0%	null
inst-strata-L01-015-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-015-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-015-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-015-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-015-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-015-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-015-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-015-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-015-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-015-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-015-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-015-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-015-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-015-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-015-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L01-015-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-015-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L01-015-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-015-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-015-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-015-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-015-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-015-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "parish register", "value": 2 }
inst-strata-L01-015-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-015-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-015-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-016-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-016-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-016-maritime--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-016-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L01-016-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-016-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	claude-fable-5.1	transport_error	—	null
inst-strata-L01-016-maritime--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-016-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-016-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-016-maritime--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-016-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-016-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-016-maritime--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-016-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-016-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-016-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "pilot's note", "value": "3" }
inst-strata-L01-016-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-016-maritime--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 3 }
inst-strata-L01-016-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-017-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-017-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-017-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-017-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-017-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L01-017-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L01-017-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-017-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-017-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-017-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-017-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-017-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-017-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-017-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-017-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L01-017-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-017-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-017-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-017-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-017-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Odile" }
inst-strata-L01-017-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-017-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L01-017-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-018-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-018-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-018-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-018-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-018-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L01-018-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-018-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-018-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-018-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-018-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-018-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L01-018-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-018-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L01-018-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-018-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-018-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L01-018-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-018-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "tithe receipt", "value": 4 }
inst-strata-L01-018-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-019-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L01-019-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-019-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L01-019-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-019-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-019-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	glm-5.3-flash	transport_error	—	null
inst-strata-L01-019-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-019-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-019-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L01-019-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L01-019-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-019-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L01-019-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "rehearsal log", "value": "2" }
inst-strata-L01-019-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L01-019-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L01-019-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L01-019-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L01-019-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "rehearsal log", "value": 2 }
inst-strata-L01-019-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Configured level: 2
Instance	Provider	Status	Correct	Submitted action
inst-strata-L02-000-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-000-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-000-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-000-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-000-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-000-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-000-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-000-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-000-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-000-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-000-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-000-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-000-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "aurora watch", "value": "Cassia" }
inst-strata-L02-000-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-001-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-001-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L02-001-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-001-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-001-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-001-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "register", "subject": "left-luggage ticket", "value": "Lyra" }
inst-strata-L02-001-hotel--explicit-r2	gpt-6-luna	invalid_response	0.0%	null
inst-strata-L02-001-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-001-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-001-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-001-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-001-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-001-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-001-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-001-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-001-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-001-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-001-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-001-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-001-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L02-001-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L02-001-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L02-001-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "left-luggage ticket", "value": "Halden" }
inst-strata-L02-001-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-001-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-001-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-002-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-002-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-002-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-002-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-002-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L02-002-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-002-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-002-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-002-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-002-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-002-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-002-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-002-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-002-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-002-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-002-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-002-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-002-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "consignment tag", "value": "Marek" }
inst-strata-L02-002-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-002-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-002-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-003-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-003-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "switchboard log", "value": "3" }
inst-strata-L02-003-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-003-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-003-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-003-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "switchboard log", "value": "3" }
inst-strata-L02-003-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-003-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-003-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-003-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-003-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-003-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-003-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-003-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-003-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-003-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "switchboard log", "value": "3" }
inst-strata-L02-003-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-003-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-003-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-003-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L02-003-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "switchboard log", "value": 3 }
inst-strata-L02-003-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-003-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-003-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-004-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-004-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-004-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-004-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-004-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-004-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-004-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-004-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L02-004-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-004-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-004-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-004-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-004-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-004-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	glm-5.3	invalid_response	0.0%	null
inst-strata-L02-004-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-004-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-004-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-004-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-004-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Halden" }
inst-strata-L02-004-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-004-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-004-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-005-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-005-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-005-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-005-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-005-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-005-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-005-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "ticket manifest", "value": "4" }
inst-strata-L02-005-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-005-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-005-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-005-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-005-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-005-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-005-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-005-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-005-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-005-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	glm-5.3-flash	answered	0.0%	{ "operation": "register", "subject": "ticket manifest", "value": 3 }
inst-strata-L02-005-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-005-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-005-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-005-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "ticket manifest", "value": 4 }
inst-strata-L02-005-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "ticket manifest", "value": "4" }
inst-strata-L02-005-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-005-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-005-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-006-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-006-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-006-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-006-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-006-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-006-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-006-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-006-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-006-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-006-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-006-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-006-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-006-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "plate register", "value": "2" }
inst-strata-L02-006-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-006-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-006-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "plate register", "value": 2 }
inst-strata-L02-006-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-006-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-006-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-007-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin's mark" }
inst-strata-L02-007-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L02-007-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-007-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-007-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-007-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-007-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-fable-5	invalid_response	0.0%	null
inst-strata-L02-007-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-007-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-007-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-007-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-007-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L02-007-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-007-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-007-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-007-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L02-007-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-007-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-007-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-007-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-007-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-007-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-007-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-007-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "mess roster", "value": "Corin" }
inst-strata-L02-007-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "mess roster", "value": 1 }
inst-strata-L02-007-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-007-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-007-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-008-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-008-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L02-008-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-008-hotel--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-008-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-008-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-008-hotel--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-008-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-008-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-008-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-008-hotel--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-008-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-008-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-008-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-008-hotel--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-008-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-008-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile's mark" }
inst-strata-L02-008-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-008-hotel--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cellar card", "value": "Odile" }
inst-strata-L02-008-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-009-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "cryostat sheet", "value": "1" }
inst-strata-L02-009-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-009-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-009-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-009-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L02-009-observatory--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-009-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-009-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-009-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L02-009-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-009-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-009-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-009-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-009-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	glm-5.3-flash	invalid_response	0.0%	null
inst-strata-L02-009-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "cryostat sheet", "value": "1" }
inst-strata-L02-009-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-009-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "cryostat sheet", "value": 1 }
inst-strata-L02-009-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-010-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L02-010-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-010-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-010-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-010-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L02-010-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "power schedule", "value": "4" }
inst-strata-L02-010-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-010-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-010-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-010-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L02-010-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-010-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-010-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-010-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-010-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-010-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-010-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-010-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-010-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-010-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-010-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "power schedule", "value": 4 }
inst-strata-L02-010-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "power schedule", "value": "4" }
inst-strata-L02-010-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-010-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-010-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-011-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-011-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-011-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-011-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	grok-4.6	answered	0.0%	null
inst-strata-L02-011-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-011-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-011-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-011-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-011-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-011-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-011-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-011-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-011-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L02-011-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-011-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-011-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-011-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-011-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 2 }
inst-strata-L02-011-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-011-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-011-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-012-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-012-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-012-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-012-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-012-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L02-012-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	glm-5.3-flash	transport_error	—	null
inst-strata-L02-012-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-012-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-012-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-012-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-012-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-012-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-012-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-012-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-012-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-haiku-4.5	answered	0.0%	null
inst-strata-L02-012-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-012-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-012-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-012-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-012-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L02-012-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": "Vela" }
inst-strata-L02-012-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-012-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-012-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-013-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-013-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-013-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L02-013-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-013-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-013-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "register", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-013-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-013-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-013-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-013-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-013-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-013-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-013-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-013-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": "2" }
inst-strata-L02-013-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-013-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-013-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L02-013-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "register", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-013-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "carrier's waybill", "value": 2 }
inst-strata-L02-013-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-014-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gemini-3.8-flash	transport_error	—	null
inst-strata-L02-014-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-014-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-014-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-014-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-014-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-014-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-014-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-014-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-014-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-014-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-014-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-014-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-014-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-014-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-014-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-014-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L02-014-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "funicular ticket", "value": "Galia" }
inst-strata-L02-014-hotel--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L02-014-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-014-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-014-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-015-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-015-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-015-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-015-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-015-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-015-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-015-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-015-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-015-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-015-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-015-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-015-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-015-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Sable" }
inst-strata-L02-015-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-015-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-015-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-015-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-015-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-015-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wardrobe ledger", "value": "Bram" }
inst-strata-L02-015-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-015-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-015-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-016-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-016-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-016-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-016-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-016-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-016-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-016-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-016-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-016-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L02-016-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-016-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-016-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-016-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-016-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-016-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-016-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-016-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-016-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-016-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "terrace menu", "value": "Ferro" }
inst-strata-L02-016-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-016-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-016-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-017-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-017-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-017-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-017-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-017-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-017-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-017-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "stage manager's log", "value": "1" }
inst-strata-L02-017-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-017-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-017-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-017-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-017-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-017-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-017-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L02-017-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-017-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 1 }
inst-strata-L02-017-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-018-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-018-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L02-018-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-018-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-018-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-018-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-018-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-018-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-018-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-018-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-018-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "wool account", "value": "3" }
inst-strata-L02-018-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-018-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-018-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-018-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-018-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "wool account", "value": 3 }
inst-strata-L02-018-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-019-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "tide-table entry", "value": "2" }
inst-strata-L02-019-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "tide-table entry", "value": "2" }
inst-strata-L02-019-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-019-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-019-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-019-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-019-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-019-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-019-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-019-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L02-019-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L02-019-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L02-019-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L02-019-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-019-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-019-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L02-019-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L02-019-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L02-019-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-019-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L02-019-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	glm-5.3	transport_error	—	null
inst-strata-L02-019-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L02-019-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tide-table entry", "value": 2 }
inst-strata-L02-019-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L02-019-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L02-019-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Configured level: 3
Instance	Provider	Status	Correct	Submitted action
inst-strata-L03-000-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L03-000-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-000-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-000-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-000-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-000-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-6-sol	answered	0.0%	{ "operation": "register", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L03-000-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-000-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-000-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-000-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L03-000-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-000-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-000-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-000-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-000-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-000-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-000-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-000-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L03-000-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-haiku-4.5	answered	0.0%	null
inst-strata-L03-000-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-000-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-000-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-000-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-000-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L03-000-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	minimax-m3	answered	0.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": "2" }
inst-strata-L03-000-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "chandlery invoice", "value": 2 }
inst-strata-L03-000-maritime--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L03-000-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-000-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-000-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-001-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-001-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-001-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-001-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-001-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-001-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-001-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-001-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-001-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-001-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-001-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-001-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-001-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-001-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-001-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	glm-5.3-flash	invalid_response	0.0%	null
inst-strata-L03-001-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-001-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-001-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-001-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-001-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-001-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stage manager's log", "value": 3 }
inst-strata-L03-001-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-001-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-001-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-002-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "guest register", "value": "altered after the fire" }
inst-strata-L03-002-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L03-002-hotel--explicit-r1	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L03-002-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r1	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L03-002-hotel--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-002-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-002-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-002-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-002-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "guest register", "value": "5" }
inst-strata-L03-002-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-002-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-002-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-002-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-002-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-002-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-002-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-002-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	grok-4.6	answered	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	qwen3.8-27b	answered	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-002-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-002-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-002-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "guest register", "value": 5 }
inst-strata-L03-002-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-002-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-002-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-003-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-003-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-003-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-003-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-003-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L03-003-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-003-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-003-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-003-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-003-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-003-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-003-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-003-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-003-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-003-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-003-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-003-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-003-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-003-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-003-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "prop list", "value": 3 }
inst-strata-L03-003-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-003-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-003-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-004-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r1	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "pilot's note", "value": "4" }
inst-strata-L03-004-maritime--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-004-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-004-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-004-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-004-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-004-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-004-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-004-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-004-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-004-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-004-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-004-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-004-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-004-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-004-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-004-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-004-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-004-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-004-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L03-004-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "pilot's note", "value": 4 }
inst-strata-L03-004-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-004-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-004-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-005-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": "2" }
inst-strata-L03-005-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-005-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-005-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-005-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L03-005-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-005-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-005-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-005-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L03-005-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-005-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-005-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-005-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-005-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-005-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	claude-opus-5.5	answered	0.0%	null
inst-strata-L03-005-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L03-005-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-005-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-005-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-005-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-005-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-005-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L03-005-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": 2 }
inst-strata-L03-005-hotel--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "shuttle manifest", "value": "2" }
inst-strata-L03-005-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-005-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-005-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-006-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-006-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-006-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-006-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-006-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-006-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-006-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-006-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-006-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-006-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-006-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-006-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-006-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-006-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-006-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-006-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-006-observatory--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-006-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": 4 }
inst-strata-L03-006-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-007-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-007-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-007-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-007-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-007-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-007-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-007-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-007-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-007-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-007-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-007-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-007-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-007-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-007-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-007-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-007-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-007-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "tape index", "value": "Petra" }
inst-strata-L03-007-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-007-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-007-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-008-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-008-theater--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "box-office tally", "value": "2" }
inst-strata-L03-008-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-008-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-008-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-008-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L03-008-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L03-008-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "register", "subject": "box-office tally", "value": "2" }
inst-strata-L03-008-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-008-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-008-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-008-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-008-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "box-office tally", "value": "2" }
inst-strata-L03-008-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-008-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-008-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-008-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-008-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "box-office tally", "value": 2 }
inst-strata-L03-008-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-009-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L03-009-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-009-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-009-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-009-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-009-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-009-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "seeing report", "value": "1" }
inst-strata-L03-009-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-009-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-009-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	glm-5.3	invalid_response	0.0%	null
inst-strata-L03-009-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-009-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-009-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-009-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L03-009-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-009-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L03-009-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-009-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seeing report", "value": 1 }
inst-strata-L03-009-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-010-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gpt-6-sol	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	glm-5.3	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gemini-3.6-flash	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-fable-5	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r1	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-010-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-010-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-010-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	glm-5.3	invalid_response	0.0%	null
inst-strata-L03-010-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-010-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-010-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-010-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r1	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-010-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-010-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "generator book", "value": 3 }
inst-strata-L03-010-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-011-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-011-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-011-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-011-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-011-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-011-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-011-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-011-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-011-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-011-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-011-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-011-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-011-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "stable diary", "value": "Bram" }
inst-strata-L03-011-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-012-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-012-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-012-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-012-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-012-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L03-012-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-012-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-012-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-012-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-012-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-012-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-012-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-012-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-012-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-012-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-012-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-012-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Lyra" }
inst-strata-L03-012-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-013-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-013-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-013-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-013-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L03-013-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-013-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-013-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-013-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-013-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-013-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-013-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-013-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-013-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-013-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	minimax-m3	answered	0.0%	null
inst-strata-L03-013-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r1	claude-haiku-4.5	answered	0.0%	null
inst-strata-L03-013-hotel--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-013-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-013-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-013-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-013-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "wax-bench log", "value": "Cassia" }
inst-strata-L03-013-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-013-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-013-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-014-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-014-hotel--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-014-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-014-hotel--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-014-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L03-014-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-014-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-014-hotel--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-014-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-014-hotel--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-014-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-014-hotel--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "night auditor sheet", "value": "Petra" }
inst-strata-L03-014-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-015-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L03-015-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-haiku-4.5	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-015-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-015-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-015-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-015-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-015-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-015-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-015-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-015-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-015-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-015-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-015-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-015-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-015-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-015-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-015-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-015-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-015-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Marek" }
inst-strata-L03-015-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-015-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-015-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-016-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L03-016-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-016-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-016-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-016-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-016-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-016-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-016-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-016-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-016-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-016-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-016-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-016-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-016-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-016-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-016-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-016-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seating chart", "value": "Sable" }
inst-strata-L03-016-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-016-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-016-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-017-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-017-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	glm-5.3-flash	invalid_response	0.0%	null
inst-strata-L03-017-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-017-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-017-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-017-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-017-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-017-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-017-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-017-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L03-017-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-017-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-017-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-017-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-017-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-017-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-017-theater--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r1	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L03-017-theater--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-017-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-017-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-017-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-017-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "understudy roster", "value": "green-room register" }
inst-strata-L03-017-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-017-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-017-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "understudy roster", "value": 2 }
inst-strata-L03-017-theater--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L03-017-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-017-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-017-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-018-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "prop list", "value": "5" }
inst-strata-L03-018-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L03-018-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-018-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-018-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-018-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L03-018-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-018-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-018-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-018-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-018-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L03-018-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-018-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-018-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-018-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-018-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-018-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-018-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-018-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "prop list", "value": 5 }
inst-strata-L03-018-theater--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "prop list", "value": "5" }
inst-strata-L03-018-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-018-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L03-018-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-019-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-019-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": "5" }
inst-strata-L03-019-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-019-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-019-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-019-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-019-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L03-019-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-019-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-019-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L03-019-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L03-019-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	minimax-m3	invalid_response	0.0%	null
inst-strata-L03-019-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L03-019-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-019-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L03-019-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L03-019-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": "5" }
inst-strata-L03-019-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L03-019-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "cryostat sheet", "value": 5 }
inst-strata-L03-019-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Configured level: 4
Instance	Provider	Status	Correct	Submitted action
inst-strata-L04-000-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	glm-5.3	invalid_response	0.0%	null
inst-strata-L04-000-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-000-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-000-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	deepseek-v4-pro	answered	0.0%	null
inst-strata-L04-000-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile's mark" }
inst-strata-L04-000-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-000-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-000-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-000-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-000-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-000-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-000-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-000-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-000-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-000-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "register", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L04-000-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-000-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile's mark" }
inst-strata-L04-000-observatory--implicit-r2	minimax-m3	answered	0.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile's mark" }
inst-strata-L04-000-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	claude-haiku-4.5	answered	0.0%	null
inst-strata-L04-000-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "flare alert sheet", "value": "Odile's mark" }
inst-strata-L04-000-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-000-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "flare alert sheet", "value": "Odile" }
inst-strata-L04-000-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-001-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-6-sol	answered	0.0%	null
inst-strata-L04-001-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	deepseek-4.1-flash	transport_error	—	null
inst-strata-L04-001-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	claude-opus-5.5	answered	0.0%	null
inst-strata-L04-001-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-001-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-001-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-001-theater--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-001-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-001-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-001-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-001-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-001-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-001-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-001-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-001-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-001-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-001-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-001-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	claude-opus-5.5	answered	0.0%	null
inst-strata-L04-001-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-001-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "call sheet", "value": "1" }
inst-strata-L04-001-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-001-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-001-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-001-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L04-001-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "call sheet", "value": 1 }
inst-strata-L04-001-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-001-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-001-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-002-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-002-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "kennel book", "value": "4" }
inst-strata-L04-002-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-002-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-002-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-002-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L04-002-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-002-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-002-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-002-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-002-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L04-002-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-002-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-002-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-002-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-002-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-002-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-002-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-002-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-002-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gemini-3.8-flash	transport_error	—	null
inst-strata-L04-002-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "kennel book", "value": 4 }
inst-strata-L04-002-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-002-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-002-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-003-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	deepseek-4.1-flash	transport_error	—	null
inst-strata-L04-003-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	mimo-v2.6-flash	transport_error	—	null
inst-strata-L04-003-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-003-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-003-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-003-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-003-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	minimax-m3	invalid_response	0.0%	null
inst-strata-L04-003-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-003-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-003-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-003-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-003-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-003-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-003-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-003-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-003-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-003-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-003-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-003-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-003-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": "Wren" }
inst-strata-L04-003-hotel--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-003-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-003-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-003-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-004-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-004-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-004-maritime--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L04-004-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-004-maritime--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-004-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-004-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-004-maritime--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-004-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L04-004-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-004-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-004-maritime--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-004-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-004-maritime--implicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-004-maritime--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-004-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-004-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-004-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-004-maritime--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": 1 }
inst-strata-L04-004-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	baseline:forward-chain	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gemini-3.7-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gemini-3.8-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	deepseek-4.1-flash	transport_error	—	null
inst-strata-L04-005-hotel--explicit-r1	gemini-3.6-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": 1 }
inst-strata-L04-005-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	grok-4.6	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r1	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-005-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-005-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	baseline:forward-chain	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	gpt-6-sol	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": "unresolved" }
inst-strata-L04-005-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L04-005-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	grok-4.6	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	minimax-m3	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	kimi-k3	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": 2 }
inst-strata-L04-005-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--explicit-r2	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-005-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-005-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-005-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-005-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	baseline:forward-chain	answered	0.0%	null
inst-strata-L04-005-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-005-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-005-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-005-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-005-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	baseline:forward-chain	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L04-005-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	gemini-3.7-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	gpt-5.6-terra	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": 1 }
inst-strata-L04-005-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	gemini-3.6-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": "Halden" }
inst-strata-L04-005-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-005-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	grok-4.6	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	minimax-m3	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r1	claude-haiku-4.5	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-005-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-005-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	baseline:forward-chain	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gemini-3.6-flash	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	gpt-5.6-luna	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": 1 }
inst-strata-L04-005-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-005-hotel--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cellar card", "value": 5 }
inst-strata-L04-005-hotel--implicit-r2	claude-haiku-4.5	answered	0.0%	{ "operation": "hold", "subject": "cellar card", "value": 1 }
inst-strata-L04-005-hotel--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-005-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-005-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-005-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-006-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-006-hotel--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-006-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-006-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-006-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-006-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-006-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-006-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-006-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-006-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-006-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-006-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-006-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-006-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-006-hotel--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-006-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-006-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-006-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-006-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cashier's drop slip", "value": "Dover" }
inst-strata-L04-006-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-006-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-006-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-007-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-007-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-007-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-007-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-007-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-007-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-007-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-007-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-007-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-007-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-007-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-007-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-007-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-007-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-007-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-007-manor--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-007-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "apiary log", "value": "Corin" }
inst-strata-L04-007-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-008-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "filter log", "value": "3" }
inst-strata-L04-008-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-008-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-008-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-008-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-008-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-008-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-008-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-008-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L04-008-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-008-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-008-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-008-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-008-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-008-observatory--implicit-r1	gpt-5.6-luna	invalid_response	0.0%	null
inst-strata-L04-008-observatory--implicit-r1	claude-opus-5.5	content_filter	—	null
inst-strata-L04-008-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-008-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-008-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-008-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-008-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "filter log", "value": "3" }
inst-strata-L04-008-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "filter log", "value": 3 }
inst-strata-L04-008-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "filter log", "value": "3" }
inst-strata-L04-008-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-008-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-008-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-009-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-009-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	glm-5.3-flash	answered	0.0%	{ "operation": "register", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-009-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-009-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-009-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-009-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-009-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-009-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-009-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-009-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-009-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-009-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-009-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-009-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-009-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-009-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-009-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-009-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighthouse log", "value": "Wren" }
inst-strata-L04-009-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-009-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-009-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-010-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L04-010-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-010-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-010-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-010-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-010-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-010-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-fable-5	answered	0.0%	{ "operation": "hold", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-010-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-010-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-010-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-010-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-010-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-010-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-010-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-010-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-010-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-fable-5	answered	0.0%	{ "operation": "hold", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-010-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "tape index", "value": 3 }
inst-strata-L04-010-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-011-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-011-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-011-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-011-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-011-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-011-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	claude-fable-5	transport_error	—	null
inst-strata-L04-011-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L04-011-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-011-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "instrument log", "value": "wrong drop" }
inst-strata-L04-011-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-011-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-011-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-011-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-011-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-011-observatory--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-011-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-011-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-011-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-011-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-011-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-011-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "instrument log", "value": 4 }
inst-strata-L04-011-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-011-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-011-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-012-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	deepseek-4.1-flash	transport_error	—	null
inst-strata-L04-012-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-012-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-012-theater--explicit-r1	glm-5.3-flash	answered	0.0%	{ "operation": "register", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-012-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-012-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-012-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L04-012-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-012-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-012-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-012-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-012-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-012-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-012-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-012-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-012-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-012-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-012-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-012-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-012-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-012-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-012-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-012-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-012-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "hotel chit", "value": 5 }
inst-strata-L04-012-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-012-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-012-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-013-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-013-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-013-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-013-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-013-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-013-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-013-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-013-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-013-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-013-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-013-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-013-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-013-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-013-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-013-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	glm-5.3	invalid_response	0.0%	null
inst-strata-L04-013-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-013-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-013-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-013-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-013-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L04-013-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-013-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	kimi-k3	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "green-room register", "value": 5 }
inst-strata-L04-013-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-013-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-013-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-014-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	glm-5.3	invalid_response	0.0%	null
inst-strata-L04-014-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-014-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-014-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-014-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-014-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-014-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-014-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-014-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-014-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-014-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-014-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-014-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-014-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-014-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-014-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-014-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-014-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-014-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-014-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": "5" }
inst-strata-L04-014-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-014-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-014-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-014-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-014-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-014-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-014-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "churchwarden's book", "value": 5 }
inst-strata-L04-014-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-014-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-014-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-015-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L04-015-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-015-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-015-observatory--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-015-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-015-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-015-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-015-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-015-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-015-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-015-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-015-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-015-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-015-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	minimax-m3	invalid_response	0.0%	null
inst-strata-L04-015-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-015-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L04-015-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-015-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-015-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-015-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-015-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L04-015-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-015-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-015-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-015-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-015-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-015-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-015-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": "Tomas" }
inst-strata-L04-015-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-015-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-015-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-016-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-016-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-016-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-016-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-016-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-016-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-016-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L04-016-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-016-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-016-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-016-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-016-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-016-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-016-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-016-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-016-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-016-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-016-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L04-016-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-016-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-016-observatory--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-016-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-016-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L04-016-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-016-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L04-016-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-016-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dome log", "value": "Juno" }
inst-strata-L04-016-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-016-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-016-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-017-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L04-017-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-017-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	claude-opus-5.5	content_filter	—	null
inst-strata-L04-017-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-017-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-017-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-017-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-017-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-017-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-017-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-017-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-017-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-017-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-017-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-017-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-017-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-017-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-017-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	deepseek-v4-pro	answered	0.0%	null
inst-strata-L04-017-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-017-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-017-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r1	claude-haiku-4.5	answered	0.0%	null
inst-strata-L04-017-observatory--implicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L04-017-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-017-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-017-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-017-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	glm-5.3	transport_error	—	null
inst-strata-L04-017-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-017-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-017-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "aurora watch", "value": 1 }
inst-strata-L04-017-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-017-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-017-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-018-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-018-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-018-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-018-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-018-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-018-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-018-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-018-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-018-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-018-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-018-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L04-018-hotel--formal-r0	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-018-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-018-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-018-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-018-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-018-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-018-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L04-018-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-018-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-018-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-018-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-018-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L04-018-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-018-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-018-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "housekeeping sheet", "value": "Lyra" }
inst-strata-L04-018-hotel--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L04-018-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-018-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-018-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-019-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-019-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-019-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-019-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-019-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-019-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-019-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-019-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-019-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-019-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-019-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-019-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L04-019-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	qwen3.8-27b	invalid_response	0.0%	null
inst-strata-L04-019-maritime--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L04-019-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L04-019-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L04-019-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-019-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-019-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L04-019-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L04-019-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L04-019-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L04-019-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L04-019-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-019-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L04-019-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L04-019-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L04-019-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "harbor manifest", "value": "Sable" }
inst-strata-L04-019-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L04-019-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L04-019-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Configured level: 5
Instance	Provider	Status	Correct	Submitted action
inst-strata-L05-000-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-000-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-000-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-000-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-000-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-000-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L05-000-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-000-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-000-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-000-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-000-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-000-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-000-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-000-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-000-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-000-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-000-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-000-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-000-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r1	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L05-000-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-000-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-000-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-000-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L05-000-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-000-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-000-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": 1 }
inst-strata-L05-000-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-000-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-000-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-001-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-001-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "watch rotation", "value": "2" }
inst-strata-L05-001-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-001-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-001-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-001-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-001-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-001-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-001-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-001-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-001-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-001-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-001-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-001-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L05-001-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-001-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-001-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-001-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "watch rotation", "value": "2" }
inst-strata-L05-001-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-001-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-001-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-001-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-001-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-001-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "watch rotation", "value": 2 }
inst-strata-L05-001-maritime--implicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L05-001-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-001-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-001-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-002-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-002-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-002-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "storm glass", "value": "3" }
inst-strata-L05-002-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-002-maritime--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-002-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gemini-3.6-flash	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-002-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-002-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-002-maritime--explicit-r2	glm-5.3-flash	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-002-maritime--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-002-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-002-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-002-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-002-maritime--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-002-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-002-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-002-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-002-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-opus-5.5	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-fable-5	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L05-002-maritime--implicit-r2	grok-4.6	answered	0.0%	{ "operation": "hold", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-002-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-002-maritime--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "storm glass", "value": 3 }
inst-strata-L05-002-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-003-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-003-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-003-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-003-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-003-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-003-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-003-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-003-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-003-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-003-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	minimax-m3	invalid_response	0.0%	null
inst-strata-L05-003-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-003-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-003-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-003-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-003-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-003-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-003-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-003-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-003-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-003-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-003-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-003-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "dressmaker's bill", "value": 2 }
inst-strata-L05-003-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-004-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-004-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-004-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-004-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-004-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-004-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L05-004-maritime--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-004-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-004-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	kimi-k2.6	answered	0.0%	{ "operation": "hold", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-004-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-004-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-004-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-004-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L05-004-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-004-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-004-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-004-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-004-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-004-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L05-004-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-004-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-haiku-4.5	answered	0.0%	{ "operation": "register", "subject": "dock_pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-004-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-004-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	deepseek-v4-pro	answered	0.0%	{ "operation": "hold", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-004-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "dock pass", "value": "Halden" }
inst-strata-L05-004-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-004-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-004-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-005-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-005-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-005-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-005-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	claude-opus-5.5	content_filter	—	null
inst-strata-L05-005-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-005-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	kimi-k2.6	transport_error	—	null
inst-strata-L05-005-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-005-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-005-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-005-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L05-005-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L05-005-theater--formal-r0	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L05-005-theater--formal-r0	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-005-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-005-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-005-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-005-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-005-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	glm-5.3	transport_error	—	null
inst-strata-L05-005-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-005-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	kimi-k3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-005-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-005-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-005-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-005-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-005-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-005-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "fly schedule", "value": "Iris" }
inst-strata-L05-005-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-006-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-006-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-006-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-006-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-006-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-006-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-006-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-006-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-006-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-006-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L05-006-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-006-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-006-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-006-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-006-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-006-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L05-006-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-006-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-006-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-006-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-006-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-006-hotel--implicit-r2	glm-5.3-flash	answered	0.0%	{ "operation": "register", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry chit", "value": 3 }
inst-strata-L05-006-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-006-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-006-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-007-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-007-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-007-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-007-manor--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-007-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-007-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-007-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-007-manor--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-007-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-007-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-007-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-007-manor--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-007-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-007-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-007-manor--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L05-007-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-007-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-007-manor--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-007-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-007-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-007-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-007-manor--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "seed ledger", "value": "Wren" }
inst-strata-L05-007-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-008-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-008-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-008-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-008-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-008-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "per diem sheet", "value": "4" }
inst-strata-L05-008-theater--explicit-r2	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-008-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-008-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-008-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-008-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-008-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-008-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-008-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-008-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-008-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-008-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-008-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-008-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-008-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-008-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "per diem sheet", "value": 4 }
inst-strata-L05-008-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-009-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L05-009-theater--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-009-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-009-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-009-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-009-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-009-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-009-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-009-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-009-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-009-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-009-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L05-009-theater--formal-r0	mimo-v2.6-flash	answered	0.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": "2" }
inst-strata-L05-009-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-009-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-009-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-009-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-009-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-009-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": "2" }
inst-strata-L05-009-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-009-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-009-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-009-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-009-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	deepseek-4.1-flash	transport_error	—	null
inst-strata-L05-009-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-009-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "laundry bundle chit", "value": 2 }
inst-strata-L05-009-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-009-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-009-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-010-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	glm-5.3	transport_error	—	null
inst-strata-L05-010-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-010-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-010-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-010-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-010-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-010-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-010-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-010-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-010-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-010-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-010-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L05-010-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L05-010-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-010-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-010-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-010-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-010-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-010-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-010-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-010-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-010-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-010-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-010-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-010-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "advance booking sheet", "value": "Cassia" }
inst-strata-L05-010-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-010-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-010-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-011-hotel--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-011-hotel--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-011-hotel--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-011-hotel--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-011-hotel--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-011-hotel--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-011-hotel--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-011-hotel--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "valet_ticket", "value": "Silas" }
inst-strata-L05-011-hotel--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-011-hotel--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-011-hotel--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-011-hotel--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-011-hotel--formal-r0	gpt-6-sol	invalid_response	0.0%	null
inst-strata-L05-011-hotel--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-fable-5	content_filter	—	null
inst-strata-L05-011-hotel--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-011-hotel--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-011-hotel--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-011-hotel--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-011-hotel--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-011-hotel--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-011-hotel--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-011-hotel--implicit-r1	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-011-hotel--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-011-hotel--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-011-hotel--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-011-hotel--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-011-hotel--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-011-hotel--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "valet ticket", "value": "Silas" }
inst-strata-L05-011-hotel--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-011-hotel--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-011-hotel--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-012-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-012-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-012-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-012-observatory--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-012-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-012-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-012-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-012-observatory--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-012-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-012-observatory--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-012-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-012-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-012-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-012-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-012-observatory--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-012-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-012-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-012-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-012-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-012-observatory--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-012-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-012-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-012-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-012-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-012-observatory--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "generator book", "value": "Galia" }
inst-strata-L05-012-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-013-observatory--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-013-observatory--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-013-observatory--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-013-observatory--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-013-observatory--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-013-observatory--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-013-observatory--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-013-observatory--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-013-observatory--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L05-013-observatory--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-013-observatory--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	glm-4.7-flash	answered	0.0%	{ "operation": "register", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-013-observatory--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-013-observatory--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-013-observatory--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-013-observatory--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-013-observatory--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-013-observatory--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-013-observatory--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-013-observatory--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	claude-opus-5.5	answered	0.0%	null
inst-strata-L05-013-observatory--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	claude-opus-5	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-013-observatory--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-013-observatory--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-013-observatory--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-013-observatory--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-013-observatory--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "snow-cat log", "value": "Petra" }
inst-strata-L05-013-observatory--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-013-observatory--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-013-observatory--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-014-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-014-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-014-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-014-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-014-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-014-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-014-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-014-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-014-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-014-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-014-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-014-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-014-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-014-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-014-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-014-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-014-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-014-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-014-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-014-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-014-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-014-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-014-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-014-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-014-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "register", "subject": "stage manager's log", "value": 3 }
inst-strata-L05-014-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-015-maritime--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-015-maritime--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-015-maritime--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-015-maritime--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L05-015-maritime--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-015-maritime--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-015-maritime--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-015-maritime--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-015-maritime--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L05-015-maritime--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L05-015-maritime--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-015-maritime--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	claude-haiku-4.5	invalid_response	0.0%	null
inst-strata-L05-015-maritime--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-015-maritime--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-015-maritime--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-015-maritime--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-015-maritime--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-015-maritime--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-015-maritime--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-015-maritime--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-015-maritime--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-015-maritime--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-015-maritime--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-015-maritime--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-015-maritime--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-015-maritime--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-015-maritime--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-015-maritime--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	claude-opus-5.5	answered	0.0%	null
inst-strata-L05-015-maritime--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-015-maritime--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "customs seal", "value": 3 }
inst-strata-L05-015-maritime--implicit-r2	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L05-015-maritime--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-015-maritime--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-015-maritime--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-016-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-016-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-016-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-016-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-016-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r1	glm-4.7-flash	answered	0.0%	{ "operation": "hold", "subject": "cheese room slate", "value": "1" }
inst-strata-L05-016-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-016-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-016-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-016-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-016-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gpt-6-luna	answered	0.0%	{ "operation": "register", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	mimo-v2.6-flash	invalid_response	0.0%	null
inst-strata-L05-016-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-016-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--explicit-r2	glm-4.7-flash	transport_error	—	null
inst-strata-L05-016-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-016-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-016-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-016-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gpt-6-astra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-sonnet-5	invalid_response	0.0%	null
inst-strata-L05-016-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-016-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-016-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-016-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-016-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-016-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-016-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-016-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-016-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	minimax-m3	answered	0.0%	{ "operation": "hold", "subject": "cheese room slate", "value": "1" }
inst-strata-L05-016-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-016-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-016-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-016-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-016-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-016-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-016-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "cheese room slate", "value": 1 }
inst-strata-L05-016-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-016-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-016-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-017-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-017-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-017-theater--explicit-r1	glm-5.3-flash	answered	0.0%	{ "operation": "register", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-017-theater--explicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-017-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-017-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-017-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-017-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-017-theater--explicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-017-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-017-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-017-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-017-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-017-theater--formal-r0	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-017-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-017-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	deepseek-v4-pro	invalid_response	0.0%	null
inst-strata-L05-017-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-017-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-opus-5	invalid_response	0.0%	null
inst-strata-L05-017-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-017-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-017-theater--implicit-r1	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-017-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-017-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	glm-5.3	transport_error	—	null
inst-strata-L05-017-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-017-theater--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-017-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-017-theater--implicit-r2	baseline:direct-facts	answered	100.0%	{ "operation": "hold", "subject": "armory check-out", "value": 1 }
inst-strata-L05-017-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-018-manor--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-018-manor--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-018-manor--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	mimo-v2.6-pro	invalid_response	0.0%	null
inst-strata-L05-018-manor--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-018-manor--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r1	glm-4.7-flash	transport_error	—	null
inst-strata-L05-018-manor--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-018-manor--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-018-manor--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-018-manor--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-018-manor--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-018-manor--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-018-manor--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-018-manor--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-018-manor--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-018-manor--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-018-manor--formal-r0	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-018-manor--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	glm-4.7-flash	invalid_response	0.0%	null
inst-strata-L05-018-manor--formal-r0	claude-fable-5.1	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-018-manor--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-018-manor--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-018-manor--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-sonnet-5	content_filter	—	null
inst-strata-L05-018-manor--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-018-manor--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-018-manor--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-018-manor--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-018-manor--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-018-manor--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-018-manor--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-sonnet-5	content_filter	—	null
inst-strata-L05-018-manor--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-fable-5	content_filter	—	null
inst-strata-L05-018-manor--implicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-opus-5	content_filter	—	null
inst-strata-L05-018-manor--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-018-manor--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "register", "subject": "game book", "value": "Vela" }
inst-strata-L05-018-manor--implicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-018-manor--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-018-manor--implicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-019-theater--explicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-019-theater--explicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-019-theater--explicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-019-theater--explicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-019-theater--explicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-019-theater--explicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-019-theater--explicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-019-theater--explicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-019-theater--explicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--explicit-r2	claude-fable-5.1	content_filter	—	null
inst-strata-L05-019-theater--explicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-019-theater--explicit-r2	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-019-theater--formal-r0	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gpt-6-astra	transport_error	—	null
inst-strata-L05-019-theater--formal-r0	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	gpt-5.6-luna	answered	0.0%	{ "operation": "register", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	mimo-v2.6-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-opus-5	content_filter	—	null
inst-strata-L05-019-theater--formal-r0	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	kimi-k3	transport_error	—	null
inst-strata-L05-019-theater--formal-r0	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--formal-r0	claude-fable-5.1	content_filter	—	null
inst-strata-L05-019-theater--formal-r0	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-019-theater--formal-r0	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-019-theater--implicit-r1	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gpt-6-astra	transport_error	—	null
inst-strata-L05-019-theater--implicit-r1	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	glm-5.3	answered	0.0%	{ "operation": "register", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-fable-5	content_filter	—	null
inst-strata-L05-019-theater--implicit-r1	mimo-v2.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	kimi-k3	transport_error	—	null
inst-strata-L05-019-theater--implicit-r1	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r1	claude-fable-5.1	content_filter	—	null
inst-strata-L05-019-theater--implicit-r1	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-019-theater--implicit-r1	baseline:story-copy	invalid_response	0.0%	null
inst-strata-L05-019-theater--implicit-r2	baseline:constraint-solver	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	baseline:forward-chain	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gpt-6-astra	transport_error	—	null
inst-strata-L05-019-theater--implicit-r2	gpt-6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gemini-3.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gpt-5.6-sol	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gemini-3.8-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	glm-5.3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gpt-5.6-terra	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	deepseek-4.1-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gemini-3.6-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	deepseek-v4-pro	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gpt-6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-sonnet-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	gpt-5.6-luna	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-opus-5.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-fable-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	mimo-v2.6-flash	answered	0.0%	{ "operation": "register", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	mimo-v2.6-pro	answered	0.0%	{ "operation": "register", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-opus-5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	grok-4.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	kimi-k2.6	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	minimax-m3	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	qwen3.8-27b	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	kimi-k3	transport_error	—	null
inst-strata-L05-019-theater--implicit-r2	glm-5.3-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-haiku-4.5	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	glm-4.7-flash	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	claude-fable-5.1	answered	100.0%	{ "operation": "hold", "subject": "lighting plot", "value": "Ansel" }
inst-strata-L05-019-theater--implicit-r2	baseline:direct-facts	answered	0.0%	null
inst-strata-L05-019-theater--implicit-r2	baseline:story-copy	invalid_response	0.0%	null

Appendix: run provenance and generation completeness. Also available in results.json.

Generation completeness

{
  "available": 120,
  "classification": "v3",
  "complete": true,
  "conditions": [
    "formal",
    "explicit",
    "implicit"
  ],
  "expected": 120,
  "expected_variants": 600,
  "realizations": [
    1,
    2
  ]
}

Provenance

{
  "benchmark_version": "3",
  "grader_version": "3.1",
  "sources": {
    "__init__.py": "0a0b0ed757aacfdd844c7ea335c2a134019b6d309245d2cfc912b1abac872060",
    "compile.py": "d2e5c36a2baf4c6173d399a4adbf74a42d0ccb27a3a20a13b280ce757ea205d0",
    "decisions.py": "52b6b7298cb7fd7265635a435530b7b0250591aed5ecaedc411f05425a54cf9a",
    "evaluate.py": "f425359a63343d6c7ecf4218f17c962de5410e995bb915d2accf74880fc5a677",
    "experiments.py": "ce06e18d24e27eb81fd6328f1228544605c3081a765046ab0e5553dd25baac5a",
    "generator.py": "37877a6b21815a37538c68167272ee16fe9c9e0da4408f768e926d05b8bb62ee",
    "genres.py": "2a0ab884239cadc8d4175ac978854c88732e96e4b77caa8e0ed36e6ae3e6b151",
    "grading.py": "4f7336bc23085da839b18f24af79431e79e6d9a36c4551a416e72fbc90b368f1",
    "harness.py": "04c2f73bc3a143c49e9cbece56f2a4df451483e783d6aef4cc58d9faac312b77",
    "interactive.py": "030faebbbec71f4ae6eedb650278c60da432679d978a14662c6aa3c1eec78293",
    "judge.py": "9be37e0f06c7caa88d3171dd9f5bc71575c16d9441059f0b6c0d2a50a924268d",
    "llm.py": "508a5a37ac6d9071a522aa659334325f966b9552af4a098abde8cf8c12f2aad4",
    "narrative.py": "66455bc38d907edf2dfcc5668f96e5628ecfaa0e9a7c2fefcaab3bb805d93569",
    "oracle.py": "ab5878f8ed180bccc9653a0b2fc601220d0d81cbaa24a91622d764aacfc37c55",
    "pipeline.py": "e05a0889f24003a90ef4b6c4a9ce60bd50759939e839a9bc4d03377e3dc572ca",
    "populate.py": "2dab5370fd9895de2f25c92cd851dff84a642bb125d6e07666241661136577a3",
    "reporting.py": "6cf96e7d1c2ddeae233062be20facad57e41ed7cf8ebba78b5479403917fc013",
    "rng.py": "3de3ceaced32995ab61a317be204656229ad67b10a05f21736cac082b1941917",
    "sat.py": "bfbb94117dca5e649f609b388dc741d5082be17cb278c581a7da78cd3b81797d",
    "story.py": "391f2f97fd142cbd0cbcdf12fbdef194ba4377896fd315ee19ec1bddf7d1f965",
    "verify.py": "998c048a3185bd959bc34a892217314e465ec30c3efc7db94191fcff90f8e321",
    "world.py": "963011d7ec5249030aed8c33ff0faa3b9d086bdfab024095ec0852202d59628e"
  }
}