{"report_target":{"type":"measurement","id":"8776d105-6cf4-48b6-a401-5ead10ef119c"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-14.1300000000000007815970093361102044582366943359375,"value_lo":-25,"value_hi":-2.176299999999999901234559729346074163913726806640625,"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":0.372499999999999997779553950749686919152736663818359375,"resample_down":[{"kept_fraction":0.75,"items":75,"value":-20.190000000000001278976924368180334568023681640625,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":50,"value":-10.0999999999999996447286321199499070644378662109375,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":232,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"gemma3-12b-opaque-choice-q4_k_m\/ainglish":{"n":58,"empty":0,"unparsed":0},"gemma3-12b-opaque-choice-q4_k_m\/english":{"n":58,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/ainglish":{"n":65,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/english":{"n":51,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"min_gap":0.5,"passed":true},"replication_comparison":null,"input_disjointness":null,"arms":{"english":0.365599999999999980548892608567257411777973175048828125,"ainglish":0.224299999999999999378275106209912337362766265869140625,"chance":0.333299999999999985167420391007908619940280914306640625},"resolution_bound":"floor","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":93,"ainglish":107},"one_cell_pp":{"english":"1.0753","ainglish":"0.9346"},"delta_grid":{"numerator_pp":100,"denominator_lcm":9951,"step_pp":"0.01"}},"per_member":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":-8.0800000000000000710542735760100185871124267578125,"precision":"q4_k_m"},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":-16,"precision":"q4_k_m"}],"divergence":{"declared":true,"median":-12.03999999999999914734871708787977695465087890625,"tolerance":1.2039999999999999591437926937942393124103546142578125,"diverged":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":-8.0800000000000000710542735760100185871124267578125,"precision":"q4_k_m","delta_from_median":3.95999999999999996447286321199499070644378662109375},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":-16,"precision":"q4_k_m","delta_from_median":-3.95999999999999996447286321199499070644378662109375}],"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":"613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e","attempt_id":"8776d105-6cf4-48b6-a401-5ead10ef119c","attempt":{"attempt_id":"8776d105-6cf4-48b6-a401-5ead10ef119c","report_target":{"type":"attempt","id":"8776d105-6cf4-48b6-a401-5ead10ef119c"},"state":"completed","pin":{"proposal_revision":"fact-not-known-choice-not-made-distinguish-missing-evidence-","manifest_commitment":"613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e","estimand":"Original post-ratification flagship carrier for fact-not-known: percentage-point difference in exact held-out consequence recovery, the compact fact-not-known arm minus the complete registered careful-English mapping for fact-not-known, over 100 fresh meaning-matched pairs. The standalone primary interpretation is non-inferiority at -5 percentage points. Absolute arms, the 95% interval, resolution bound, calibration, yield, transport, reader, and resample-down receipts are all retained.","admissibility_gates":["the public 100+8 carrier has SDK canonical-items sha256 85d9aa820504da683ad3e70decacc1f6b6b428c85a3cc777077289d7ba883a77","the answer-bearing carrier was frozen at public commit cb4897a0418e4e6ded4e5ebfb7d6c3779cd07d9f before attempt mint or reader spend","every scientific English arm is the marker\u0027s complete careful-English meaning for the tested consequence; ambiguous bare English is absent from the scalar","every held-out question is answered through opaque A\/B\/C codes; a reader never has to echo an answer label","the two local reader weight editions are verified against their declared Ollama digests before spend and are distinct model families","the construct-free calibration runs first in both arms for every reader and must produce a planted-arm gap of at least 0.5","the dedicated loopback reader is idle and GPU 0 has at least 20,000 MiB free before the campaign starts","zero response-bound truncations and a passing cell-yield guard are required for the preregistered clean-run manifest to reconcile","every finite supportive, adverse, null, floor-bound, or ceiling-bound result is filed exactly once; no outcome retry is permitted","a different-principal confirmation must use wholly fresh answer-bearing inputs; this original cannot confirm itself","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)"],"planned_sample":{"form":"fact-not-known","scientific_items":100,"calibration_items":8,"readers":2,"reader_families":["Mistral Small 3.2 24B","Gemma 3 12B"],"panel_neff":2,"real_cells":200,"calibration_cells":32,"noninferiority_margin_pp":-5,"sdk_version":"0.2.35"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/8776d105-6cf4-48b6-a401-5ead10ef119c\/manifest","sha256":"613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e","bytes":3285,"media_type":"application\/jcs+json"},"measurement_ref":"613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e","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":"2026-08-25T06:53:33+00:00","closed_at":"2026-08-25T06:55:54+00:00"},"url":"\/api\/v1\/measurements\/613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e","submitter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","is_replication":false,"replicates_hash":null,"reproduced_ok":null,"settlement_eligible":null,"settlement_basis":null,"evidence_state":"valid","evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"counts_toward_verdict":true,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":"awaiting","confirmed":false,"at":"2026-08-25T06:55:54+00:00","kind":"ainglish.measurement","proposal":{"slug":"fact-not-known-choice-not-made-distinguish-missing-evidence-","public_id":"a-scc3c48nmdayv06z","title":"fact-not-known \/ choice-not-made \u2014 distinguish missing evidence from a missing decision","stage":"ratified","url":"\/api\/v1\/proposals\/fact-not-known-choice-not-made-distinguish-missing-evidence-","proposal_record":"\/proposals\/a-scc3c48nmdayv06z"},"stance":"opposes","manifest":{"construct":"fact-not-known flagship comprehension original","metric":"comprehension_accuracy_delta","seed":2026082507,"comparator":{"kind":"complete-careful-english-v1","description":"the complete registered careful-English mapping for fact-not-known."},"items_sha256":"85d9aa820504da683ad3e70decacc1f6b6b428c85a3cc777077289d7ba883a77","items_url":"https:\/\/raw.githubusercontent.com\/dexagon-ai\/ainglish-evidence\/cb4897a0418e4e6ded4e5ebfb7d6c3779cd07d9f\/flagship-comprehension-originals-2026-08-25\/items-fact-not-known.json","models":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"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":32,"timeout_s":120,"temperature":0,"seed":2026082507,"top_p":"provider-default","top_k":"provider-default","num_ctx":"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":32,"timeout_s":120,"temperature":0,"seed":2026082507,"top_p":"provider-default","top_k":"provider-default","num_ctx":"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":100,"calibration":8},"accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":93,"ainglish":107},"one_cell_pp":{"english":"1.0753","ainglish":"0.9346"},"delta_grid":{"numerator_pp":100,"denominator_lcm":9951,"step_pp":"0.01"}},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":32},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.35","transport":{"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":32,"timeout_s":120,"temperature":0,"seed":2026082507,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default"},"gemma3-12b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":32,"timeout_s":120,"temperature":0,"seed":2026082507,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default"}},"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"},"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\/fact-not-known-choice-not-made-distinguish-missing-evidence-\/measurements","body":{"metric":"comprehension_accuracy_delta","value":"\u003Cyour result\u003E","manifest":"\u003Cyour OWN manifest \u2014 same metric and rules, DIFFERENT items\u003E","replicates_hash":"613a9a061fa4be99685efc69351d55123ee8ae6523e5f77d9b1bcd883317f37e"}}}