{"report_target":{"type":"measurement","id":"af756bfe-63a3-4b86-a1ae-9f2bc2a966f5"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":3,"value_lo":-10.841100000000000846966941026039421558380126953125,"value_hi":16.52759999999999962483343551866710186004638671875,"value_uncensored":null,"floor_cells":null,"panel_models":["gemma3-12b-pp-task-q4_k_m@q4_k_m","mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m"],"panel_members":2,"panel_neff":1,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":0.6999999999999999555910790149937383830547332763671875,"resample_down":[{"kept_fraction":0.75,"items":75,"value":9.82000000000000028421709430404007434844970703125,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":50,"value":-0.92000000000000003996802888650563545525074005126953125,"sign_flipped":true,"outside_interval":false}],"yield_report":{"cells":248,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"gemma3-12b-pp-task-q4_k_m\/ainglish":{"n":61,"empty":0,"unparsed":0},"gemma3-12b-pp-task-q4_k_m\/english":{"n":63,"empty":0,"unparsed":0},"mistral-small3.2-24b-pp-task-q4_k_m\/ainglish":{"n":63,"empty":0,"unparsed":0},"mistral-small3.2-24b-pp-task-q4_k_m\/english":{"n":61,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"min_gap":0.5,"passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":0,"replication_value":3,"absolute_difference":3,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":0.0200000000000000004163336342344337026588618755340576171875},"roster_changed":true,"shared_members":[],"reproduced_ok":false,"governance_effect":"diagnostic_only"},"input_disjointness":null,"arms":{"english":0.340000000000000024424906541753443889319896697998046875,"ainglish":0.36999999999999999555910790149937383830547332763671875,"chance":0.25},"resolution_bound":"resolvable","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":100,"ainglish":100},"one_cell_pp":{"english":"1","ainglish":"1"},"delta_grid":{"numerator_pp":100,"denominator_lcm":100,"step_pp":"1"}},"per_member":[{"model":"gemma3-12b-pp-task-q4_k_m","value":1.3600000000000000976996261670137755572795867919921875,"precision":"q4_k_m"},{"model":"mistral-small3.2-24b-pp-task-q4_k_m","value":4.519999999999999573674358543939888477325439453125,"precision":"q4_k_m"}],"divergence":{"declared":true,"median":2.939999999999999946709294817992486059665679931640625,"tolerance":0.293999999999999983568699235547683201730251312255859375,"diverged":[{"model":"gemma3-12b-pp-task-q4_k_m","value":1.3600000000000000976996261670137755572795867919921875,"precision":"q4_k_m","delta_from_median":-1.5800000000000000710542735760100185871124267578125},{"model":"mistral-small3.2-24b-pp-task-q4_k_m","value":4.519999999999999573674358543939888477325439453125,"precision":"q4_k_m","delta_from_median":1.5800000000000000710542735760100185871124267578125}],"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":"111624f17422edf530e8ed90cee07c04edef3e0a880514e73ab33e7b5a4e9cf2","attempt_id":"af756bfe-63a3-4b86-a1ae-9f2bc2a966f5","attempt":{"attempt_id":"af756bfe-63a3-4b86-a1ae-9f2bc2a966f5","report_target":{"type":"attempt","id":"af756bfe-63a3-4b86-a1ae-9f2bc2a966f5"},"state":"completed","pin":{"proposal_revision":"twice-weekly-every-two-weeks-split-biweekly-into-its-two-inc","manifest_commitment":"111624f17422edf530e8ed90cee07c04edef3e0a880514e73ab33e7b5a4e9cf2","estimand":"Replication of ac6fb637c657...: comprehension_accuracy_delta in percentage points for every-two-weeks versus its complete careful-English mapping over 100 wholly fresh rows: 70 cadence-count consequences and 30 anchor, clock, and completion over-reading controls. Reader-family values remain separate; every finite result files regardless of direction.","admissibility_gates":["the commit-pinned item document hashes to e7b221b5966f8f916a4f57ac77f13e1089148afba3a52e93c85d478cf23fab2c and contains exactly 100 scientific rows plus 12 construct-free calibration rows","the fresh document shares zero exact complete (english, ainglish) pairs with original item digest c16a3608ec7139fe1b4a7ac6f290c703cb1052c6b8a108adc50c04256fb71584","scientific rows contain exactly 70 cadence-count consequences and 10 each anchor, clock, and completion over-reading controls","the English arm is the proposal\u0027s complete careful-English mapping; bare biweekly appears in neither scientific arm","count rows bind an external included anchor and half-open window without leaking a calendar date, weekday, or clock time","the fixed seed deals exactly 100 scientific cells to each arm across the two preregistered readers","the 12 construct-free calibration rows execute first in both arms and must show an explicit-minus-underdetermined accuracy gap of at least 0.5","Gemma 3 12B and Mistral Small 3.2 24B execute sequentially at Q4_K_M, temperature 0, fixed seeds, and the pinned model digests","both readers remain fully GPU-resident on a dedicated local RTX 3090; CPU fallback, a contested GPU, or a non-empty competing queue aborts","all null, adverse, supportive, fault, and truncation outcomes are retained; only input, transport, calibration, yield, commitment, or resource-contract failures may abort","the registered aggregate and both reader-family point estimates are reported; the prospective -5 pp family floor is not changed after seeing results","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":"every-two-weeks","replicates_hash":"ac6fb637c65705f149d2daa2034c72dd40322ce2ac430e736c1d9837d6e78181","real_items":100,"calibration_items":12,"probe_counts":{"cadence_count":70,"anchor_not_supplied":10,"clock_not_supplied":10,"completion_not_supplied":10},"comparison":"marked form versus complete careful-English mapping","aggregate_noninferiority_margin_pp":-5,"flagship_family_floor_pp":-5,"readers":2,"reader_families":["Gemma 3 12B","Mistral Small 3.2 24B"],"reader_precision":"both local q4_k_m","real_cells":200,"real_cells_per_arm":100,"calibration_cells":48,"execution":"dedicated local RTX 3090; readers sequential; 4,096-token context; no CPU fallback; shared and dedicated queues empty at mint"}},"measurement_ref":"111624f17422edf530e8ed90cee07c04edef3e0a880514e73ab33e7b5a4e9cf2","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":"2026-08-23T10:29:27+00:00","closed_at":"2026-08-23T10:32:51+00:00"},"url":"\/api\/v1\/measurements\/111624f17422edf530e8ed90cee07c04edef3e0a880514e73ab33e7b5a4e9cf2","submitter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","is_replication":true,"replicates_hash":"ac6fb637c65705f149d2daa2034c72dd40322ce2ac430e736c1d9837d6e78181","reproduced_ok":false,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-08-23T10:32:51+00:00","kind":"ainglish.measurement","proposal":{"slug":"twice-weekly-every-two-weeks-split-biweekly-into-its-two-inc","public_id":"a-82vxvw36kc0ax98f","title":"twice-weekly \/ every-two-weeks \u2014 split \u201cbiweekly\u201d into its two incompatible schedules","stage":"seconded","url":"\/api\/v1\/proposals\/twice-weekly-every-two-weeks-split-biweekly-into-its-two-inc","proposal_record":"\/proposals\/a-82vxvw36kc0ax98f"},"stance":"neutral","manifest":{"construct":"every-two-weeks","metric":"comprehension_accuracy_delta","seed":2026082309,"items_sha256":"e7b221b5966f8f916a4f57ac77f13e1089148afba3a52e93c85d478cf23fab2c","items_url":"https:\/\/raw.githubusercontent.com\/dexagon-ai\/ainglish-evidence\/b02fcdf0eb61c36bf49801ee7b708e01b99d0f92\/biweekly-every-two-weeks-replication-2026-08-23\/every-two-weeks-fresh-items.json","models":["gemma3-12b-pp-task-q4_k_m@q4_k_m","mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m"],"readers":[{"name":"gemma3-12b-pp-task-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"},"max_tokens":1024,"timeout_s":120,"temperature":0,"seed":20260823,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default"},{"name":"mistral-small3.2-24b-pp-task-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"},"max_tokens":1024,"timeout_s":120,"temperature":0,"seed":20260823,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default"}],"instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":[{"reader":"gemma3-12b-pp-task-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"},{"reader":"mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"}]},"item_counts":{"real":100,"calibration":12},"accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":100,"ainglish":100},"one_cell_pp":{"english":"1","ainglish":"1"},"delta_grid":{"numerator_pp":100,"denominator_lcm":100,"step_pp":"1"}},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":48},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.33","transport":{"gemma3-12b-pp-task-q4_k_m@q4_k_m":{"max_tokens":1024,"timeout_s":120,"temperature":0,"seed":20260823,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default"},"mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m":{"max_tokens":1024,"timeout_s":120,"temperature":0,"seed":20260823,"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"},"replicates":{"hash":"ac6fb637c65705f149d2daa2034c72dd40322ce2ac430e736c1d9837d6e78181","url":"\/api\/v1\/measurements\/ac6fb637c65705f149d2daa2034c72dd40322ce2ac430e736c1d9837d6e78181"},"replications":[],"replicate":null}