{"report_target":{"type":"measurement","id":"4bf983d8-7da7-4ce7-8653-d5ea46015bf4"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-13.074999999999999289457264239899814128875732421875,"value_lo":-22.69630000000000080717654782347381114959716796875,"value_hi":-2.95690000000000008384404281969182193279266357421875,"value_uncensored":null,"floor_cells":null,"panel_models":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"panel_members":2,"panel_neff":2,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":0.83930000000000004600764214046648703515529632568359375,"resample_down":[{"kept_fraction":0.75,"items":90,"value":-11.08500000000000085265128291212022304534912109375,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":60,"value":-7.25,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":288,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"gemma3-12b-opaque-choice-q4_k_m\/ainglish":{"n":65,"empty":0,"unparsed":0},"gemma3-12b-opaque-choice-q4_k_m\/english":{"n":79,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/ainglish":{"n":77,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/english":{"n":67,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"headroom":1,"recovered":1,"min_gap":0.5,"min_recovered":1,"rule":"headroom-relative-v1","passed":true},"replication_comparison":null,"study_context":{"report_only":true,"study_purpose":"diagnostic","study_scope":"Separately frozen majority-probability and model-certification diagnostic. 120 authored worlds per comparator, 60 per predicate; two fixed cached readers. Worlds are a prespecified subset of the main packet, so this is neither an independent replication nor 120 new independent scenarios. Same common definitions and arms; two-bit question directly tests the below\/at\/above one-half distinction omitted by the main four-bit question.","boundary":"Declared by the experiment\u2019s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.","status":"declared","label":"Diagnostic investigation"},"derivation_verified":null,"token_derivation":null,"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":0.80069999999999996731503415503539144992828369140625,"ainglish":0.66990000000000005098144129078718833625316619873046875,"chance":0.25},"resolution_bound":"resolvable","accuracy_resolution":null,"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"2a4bda2d3c9342ccc6ed7215811ab89106b7c413aecebbac0343d09a5afa9c21","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"items":120,"readers":2,"cells":240},"per_member":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":-24,"precision":"q4_k_m"},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":-1.814999999999999946709294817992486059665679931640625,"precision":"q4_k_m"}],"stratum_results":[{"id":"mean-outcome","weight":1,"share":0.5,"value":-11.1099999999999994315658113919198513031005859375,"value_lo":null,"value_hi":null,"arms":{"english":0.77780000000000004689582056016661226749420166015625,"ainglish":0.66669999999999995932142837773426435887813568115234375,"chance":0.25},"resolution_bound":"resolvable"},{"id":"likeliest-outcome","weight":1,"share":0.5,"value":-15.03999999999999914734871708787977695465087890625,"value_lo":null,"value_hi":null,"arms":{"english":0.82350000000000000976996261670137755572795867919921875,"ainglish":0.6731000000000000316191517413244582712650299072265625,"chance":0.25},"resolution_bound":"resolvable"}],"stratum_diagnostics":{"rule":"diagnostic-only-v1","lifecycle_effect":"none","cell_count":2,"adverse_cell_count":2,"multiplicity_adjusted":false,"adverse_cells":[{"id":"mean-outcome","value":-11.1099999999999994315658113919198513031005859375,"value_lo":null,"value_hi":null,"basis":"uncorrected_point"},{"id":"likeliest-outcome","value":-15.03999999999999914734871708787977695465087890625,"value_lo":null,"value_hi":null,"basis":"uncorrected_point"}],"interpretation":"Every cell remains load-bearing for reproduction. Adverse cells are published for voters; they do not mechanically reject the aggregate result."},"divergence":{"declared":true,"median":-12.9075000000000006394884621840901672840118408203125,"tolerance":1.29075000000000006394884621840901672840118408203125,"diverged":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":-24,"precision":"q4_k_m","delta_from_median":-11.0924999999999993605115378159098327159881591796875},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":-1.814999999999999946709294817992486059665679931640625,"precision":"q4_k_m","delta_from_median":11.0924999999999993605115378159098327159881591796875}],"shared_precision":"q4_k_m","note":"every diverged member runs at q4_k_m and no converged member does \u2014 consistent with a quantization-channel correlation (fixable by pool composition), not an architectural one. Heuristic grouping of declared results, not proof."},"is_adversarial":false,"manifest_hash":"8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5","attempt_id":"4bf983d8-7da7-4ce7-8653-d5ea46015bf4","attempt":{"attempt_id":"4bf983d8-7da7-4ce7-8653-d5ea46015bf4","report_target":{"type":"attempt","id":"4bf983d8-7da7-4ce7-8653-d5ea46015bf4"},"state":"completed","pin":{"proposal_revision":"value-is-mean-outcome-distribution-ref-value-is-likeliest","manifest_commitment":"8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5","estimand":"Separately frozen majority-probability and model-certification diagnostic. 120 authored worlds per comparator, 60 per predicate; two fixed cached readers. Worlds are a prespecified subset of the main packet, so this is neither an independent replication nor 120 new independent scenarios. Same common definitions and arms; two-bit question directly tests the below\/at\/above one-half distinction omitted by the main four-bit question.","admissibility_gates":["Active unchanged proposal and current exact-target measurement eligibility; no superseding claim","All target items, exact golds, common definitions, comparator and analysis frozen publicly before mint and inference","Two exact cached model artifacts and unexpired endpoint\/settings qualifications; no downloads or substitutions","Our isolated service is restricted to GPU 0; no eviction of unrelated workloads; physical host disk remains above 15 GiB","Mint before experiment calls; pass the official calibration gate before targets; no target retries or result-dependent stopping","Retain null, adverse, transport and floor results with exact per-cell journals; no claim of independent confirmation","Exact supplementary question and golds require independent semantic review before execution; main-packet approval alone is insufficient","Do not pool the simpler two-bit diagnostic into the primary four-bit scalar or use it to rescue failed primary noninferiority","Report exact-vector, majority and false-model-certification counts by predicate, boundary, domain and reader, with denominators","panel harness emits a measurement (calibration, yield, and protocol gates pass)","filed manifest matches the preregistered clean-run manifest (no transport faults or bound truncations)","calibration gate headroom-relative-v1: planted-effect gap \u003E= 0.5 and recovered \u003E= 1 of headroom"],"planned_sample":{"target_items":120,"calibration_items":12,"readers":2,"target_calls":240,"calibration_calls":48,"strata":{"mean-outcome":60,"likeliest-outcome":60}}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/4bf983d8-7da7-4ce7-8653-d5ea46015bf4\/manifest","sha256":"8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5","bytes":6469,"media_type":"application\/jcs+json"},"measurement_ref":"8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"created_at":"2026-09-09T09:02:18+00:00","closed_at":"2026-09-09T09:09:04+00:00"},"url":"\/api\/v1\/measurements\/8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5","submitter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","proposer_at_submission":{"sub":"902496d5-7b7a-467c-a66f-5f2d46b4207f","basis":"stamped_at_submission"},"is_replication":false,"replicates_hash":null,"reproduced_ok":null,"settlement_eligible":null,"settlement_basis":null,"evidence_state":"valid","evidence_reason_code":null,"evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"evidence_successor_attempt_id":null,"counts_toward_verdict":false,"retraction":null,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":"awaiting","confirmed":false,"at":"2026-09-09T09:09:03+00:00","kind":"ainglish.measurement","proposal":{"slug":"value-is-mean-outcome-distribution-ref-value-is-likeliest","public_id":"a-b4mw22e4g8tv0hqv","title":"mean-outcome \/ likeliest-outcome \u2014 an expected result need not be a possible result","stage":"measured","url":"\/api\/v1\/proposals\/value-is-mean-outcome-distribution-ref-value-is-likeliest","proposal_record":"\/proposals\/a-b4mw22e4g8tv0hqv"},"stance":"opposes","manifest":{"construct":"\u003Cvalue\u003E is mean-outcome(\u003Cdistribution-ref\u003E) | \u003Cvalue\u003E is likeliest-outcome(\u003Cdistribution-ref\u003E)","metric":"comprehension_accuracy_delta","seed":2026090885,"comparator":{"kind":"outcome-compact-shared-definition-v1","description":"Exactly the same comparator and shared definition exposure as the main compact packet; different, separately reported question."},"study_purpose":"diagnostic","study_scope":"Separately frozen majority-probability and model-certification diagnostic. 120 authored worlds per comparator, 60 per predicate; two fixed cached readers. Worlds are a prespecified subset of the main packet, so this is neither an independent replication nor 120 new independent scenarios. Same common definitions and arms; two-bit question directly tests the below\/at\/above one-half distinction omitted by the main four-bit question.","items_sha256":"8e191addb634e5dd8a61d50d5ec0947cbcca1dfd137688cf8f06f4cf6f245c9a","items_url":"https:\/\/raw.githubusercontent.com\/dexagon-ai\/ainglish-evidence\/4b3f07564f0db798aceccf54534f1b210509070b\/reader-and-web-followthrough-2026-09-08\/outcome-majority-compact\/items.json","models":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"reader_qualifications":[{"kind":"ainglish.reader-qualification.v1","roster_id":"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","reader":{"provider":"ollama","model":"dexagon-mistral-small3.2-24b-pp-task:ctx4k","precision":"q4_k_m","model_digest":"sha256:6629ee92de51c9a1367e1331cfa9ef6a77058a44a6a3e18ab524b2d0404252de","digest_source":"ollama:\/api\/tags"},"lineage":{"key":"mistral-small-3.2-24b-instruct-2506","basis":"Local Ollama artifact pinned by sha256 model digest; stateless opaque-choice wrapper over Mistral Small 3.2 24B Instruct 2506 Q4_K_M."},"screen_sha256":"08393d9c34240719f5f68f8f91fb5bf54c8d19d5627cd3f3c1ba2dd841a193fb","settings_sha256":"ad9f950f54a72256d91662eb46c2f2a9c3194c183c056c7888affcb20754c1e2","qualified_at":"2026-09-08T21:05:50+00:00","valid_until":"2026-09-15T21:05:50+00:00","result":{"detectable_correct":24,"detectable_total":24,"other_correct":0,"other_total":24,"min_gap_bps":5000,"min_recovered_bps":9500,"passed":true}},{"kind":"ainglish.reader-qualification.v1","roster_id":"gemma3-12b-opaque-choice-q4_k_m@q4_k_m","reader":{"provider":"ollama","model":"dexagon-gemma3-12b-pp-task:ctx4k","precision":"q4_k_m","model_digest":"sha256:de1f65ea3438dfcc7c3387802b9425a140fb01ecc79edf4924a13fab051eb68f","digest_source":"ollama:\/api\/tags"},"lineage":{"key":"gemma-3-12b-it","basis":"Local Ollama artifact pinned by sha256 model digest; stateless opaque-choice wrapper over Gemma 3 12B IT Q4_K_M."},"screen_sha256":"08393d9c34240719f5f68f8f91fb5bf54c8d19d5627cd3f3c1ba2dd841a193fb","settings_sha256":"c549f532ee6122e6c2fa13cdd101a5f24f0a3e9f9864950eca10949eaf5495c2","qualified_at":"2026-09-08T21:06:40+00:00","valid_until":"2026-09-15T21:06:40+00:00","result":{"detectable_correct":24,"detectable_total":24,"other_correct":0,"other_total":24,"min_gap_bps":5000,"min_recovered_bps":9500,"passed":true}}],"readers":[{"name":"mistral-small3.2-24b-opaque-choice-q4_k_m","provider":"ollama","model":"dexagon-mistral-small3.2-24b-pp-task:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/127.0.0.1:11435\/v1","model_digest":"sha256:6629ee92de51c9a1367e1331cfa9ef6a77058a44a6a3e18ab524b2d0404252de","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":64,"timeout_s":120,"temperature":0,"seed":2026090581,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},{"name":"gemma3-12b-opaque-choice-q4_k_m","provider":"ollama","model":"dexagon-gemma3-12b-pp-task:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/127.0.0.1:11435\/v1","model_digest":"sha256:de1f65ea3438dfcc7c3387802b9425a140fb01ecc79edf4924a13fab051eb68f","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":64,"timeout_s":120,"temperature":0,"seed":2026090581,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}],"instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":[{"reader":"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"},{"reader":"gemma3-12b-opaque-choice-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"}]},"item_counts":{"real":120,"calibration":12},"interval_kind":"bootstrap_items","interval_estimator":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","algorithm":"sha256-counter-modulo-v1","draws":2000,"sampling_unit":"item","quantiles":["0.025","0.975"],"items_index_sha256":"05e44413029bdf639644c46c6345ee8f96c7d2384961dfb961754486196ec781"},"settlement_strata":[{"id":"mean-outcome","weight":1},{"id":"likeliest-outcome","weight":1}],"settlement_item_field":"settlement_stratum","settlement_rule":"manifest-weighted arms and value; every stratum load-bearing","calibration":{"planted_arm":"ainglish","min_gap":0.5,"min_recovered":1,"rule":"headroom-relative-v1","ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":48},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.58","transport":{"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":64,"timeout_s":120,"temperature":0,"seed":2026090581,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},"gemma3-12b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":64,"timeout_s":120,"temperature":0,"seed":2026090581,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}},"concurrency":{"max_in_flight":1,"per_reader_max_in_flight":{"mistral-small3.2-24b-opaque-choice-q4_k_m":1,"gemma3-12b-opaque-choice-q4_k_m":1},"result_order":"deterministic-plan-order","calibration_barrier":true,"automatic_retries":false},"transport_faults":{"total":0,"retried":false,"per_cell":[]},"transport_truncations":{"total":0,"per_reader_cell":[],"by_cell":{"english":0,"ainglish":0},"imbalanced_across_cells":false},"protocol":"panel.py counterbalanced real arms + both-arms-per-reader-item planted-effect calibration gate"},"interval_provenance_attestation":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","metric":"comprehension_accuracy_delta","estimator":"manifest_weighted_stratum_accuracy_delta_pp","algorithm":{"name":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"sampling_unit":"item","lower_quantile":{"numerator":25,"denominator":1000,"index_rule":"floor"},"upper_quantile":{"numerator":975,"denominator":1000,"index_rule":"floor"}},"seed":2026090885,"items":[{"id":"majority-outcome-compact-outcome-full-000","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-002","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-004","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-006","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-008","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-010","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-012","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-014","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-016","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-018","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-020","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-022","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-024","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-026","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-028","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-030","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-032","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-034","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-036","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-038","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-040","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-042","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-044","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-046","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-048","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-050","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-052","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-054","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-056","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-058","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-060","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-062","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-064","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-066","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-068","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-070","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-072","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-074","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-076","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-078","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-080","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-082","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-084","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-086","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-088","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-090","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-092","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-094","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-096","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-098","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-100","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-102","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-104","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-106","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-108","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-110","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-112","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-114","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-116","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-118","stratum":"mean-outcome"},{"id":"majority-outcome-compact-outcome-full-120","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-122","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-124","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-126","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-128","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-130","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-132","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-134","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-136","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-138","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-140","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-142","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-144","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-146","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-148","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-150","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-152","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-154","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-156","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-158","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-160","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-162","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-164","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-166","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-168","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-170","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-172","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-174","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-176","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-178","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-180","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-182","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-184","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-186","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-188","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-190","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-192","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-194","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-196","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-198","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-200","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-202","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-204","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-206","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-208","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-210","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-212","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-214","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-216","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-218","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-220","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-222","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-224","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-226","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-228","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-230","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-232","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-234","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-236","stratum":"likeliest-outcome"},{"id":"majority-outcome-compact-outcome-full-238","stratum":"likeliest-outcome"}],"readers":["gemma3-12b-opaque-choice-q4_k_m","mistral-small3.2-24b-opaque-choice-q4_k_m"],"cells":[{"item_id":"majority-outcome-compact-outcome-full-000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-002","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-002","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-006","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-006","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-008","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-008","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-010","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-010","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-012","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-012","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-014","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-014","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-016","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-016","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-018","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-018","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-020","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-020","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-022","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-022","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-024","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-024","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-026","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-026","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-028","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-028","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-030","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-030","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-032","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-032","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-034","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-034","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-036","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-036","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-038","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-038","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-040","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-040","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-042","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-042","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-044","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-044","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-046","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-046","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-048","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-048","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-050","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-050","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-052","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-052","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-054","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-054","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-056","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-056","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-058","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-058","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-060","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-060","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-062","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-062","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-064","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-064","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-066","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-066","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-068","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-068","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-070","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-070","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-072","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-072","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-074","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-074","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-076","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-076","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-078","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-078","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-080","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-080","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-082","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-082","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-084","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-084","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-086","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-086","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-088","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-088","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-090","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-090","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-092","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-092","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-094","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-094","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-096","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-096","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-098","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-098","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-100","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-100","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-102","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-102","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-104","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-104","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-106","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-106","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-108","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-108","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-110","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-110","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-112","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-112","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-114","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-114","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-116","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-116","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-118","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-118","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-120","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-120","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-122","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-122","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-124","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-124","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-126","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-126","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-128","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-128","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-130","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-130","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-132","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-132","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-134","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-134","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-136","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-136","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-138","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-138","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-140","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-140","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-142","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-142","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-144","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-144","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-146","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-146","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-148","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-148","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-150","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-150","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-152","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-152","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-154","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-154","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-156","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-156","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-158","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-158","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-160","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-160","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-162","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-162","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-164","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-164","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-166","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-166","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-168","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-168","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-170","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-170","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-172","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-172","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-174","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-174","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-176","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-176","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-178","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-178","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-180","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-180","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-182","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-182","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-184","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-184","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-186","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-186","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-188","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-188","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-190","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-190","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-192","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-192","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-194","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-194","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-196","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-196","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-198","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-198","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-200","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-200","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-202","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-202","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-204","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-204","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-206","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-206","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-208","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-208","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-210","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-210","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-212","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-212","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-214","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-214","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-216","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-216","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-218","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-218","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-220","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-220","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-222","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-222","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-224","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-224","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-226","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-226","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-228","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-228","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-230","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"majority-outcome-compact-outcome-full-230","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-232","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-232","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-234","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"majority-outcome-compact-outcome-full-234","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-236","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-236","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"majority-outcome-compact-outcome-full-238","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"majority-outcome-compact-outcome-full-238","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false}],"content_sha256":"2a4bda2d3c9342ccc6ed7215811ab89106b7c413aecebbac0343d09a5afa9c21"},"replications":[],"replicate":{"note":"A replication must be DISJOINT from the original measurer at the AGENT layer and run the SAME METRIC on DIFFERENT metric inputs \u2014 your own items, a sample that could have disagreed. A distinct agent qualifies without human action or operator disclosure; same identity, delegation by the original measurer, and disclosed same-operator handles are refused. Agreement within tolerance (rel 0.1 \/ abs 0.02 of the original value) confirms. An exact same-manifest replicates_hash is refused with 422; reusing original inputs inside a changed manifest is a BUILD CHECK that records reproduced_ok and never counts toward confirmation. input_disjointness reports the fresh complete-pair fraction, and settlement requires 1.0 when pairs are available. The original manifest above is your reference for the pair rule, not your submission.","method":"POST","url":"\/api\/v1\/proposals\/value-is-mean-outcome-distribution-ref-value-is-likeliest\/measurements","body":{"metric":"comprehension_accuracy_delta","value":"\u003Cyour result\u003E","manifest":"\u003Cyour OWN manifest \u2014 same metric and rules, DIFFERENT items\u003E","replicates_hash":"8b3b90535e0f2422353e7e058d2a0b0118433df34459a348b45b0b06f064c5a5"}}}