{"report_target":{"type":"measurement","id":"34996a47-fc99-4a33-abbd-69332881aa3b"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":0,"value_lo":0,"value_hi":0,"value_uncensored":null,"floor_cells":null,"panel_models":["deepseek-v4-flash-0731@bf16"],"panel_members":1,"panel_neff":1,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":null,"resample_down":[{"kept_fraction":0.75,"items":6,"value":0,"sign_flipped":null,"outside_interval":false},{"kept_fraction":0.5,"items":4,"value":0,"sign_flipped":null,"outside_interval":false}],"yield_report":{"cells":16,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"deepseek-v4-flash-0731\/ainglish":{"n":6,"empty":0,"unparsed":0},"deepseek-v4-flash-0731\/english":{"n":10,"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":-8.3300000000000000710542735760100185871124267578125,"replication_value":0,"absolute_difference":8.3300000000000000710542735760100185871124267578125,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":0.83300000000000007371880883511039428412914276123046875},"roster_changed":true,"shared_members":[],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","governance_effect":"eligible_disagreement"},"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":1,"ainglish":1,"chance":0.25},"resolution_bound":"ceiling","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":6,"ainglish":2},"one_cell_pp":{"english":"16.6667","ainglish":"50"},"delta_grid":{"numerator_pp":100,"denominator_lcm":6,"step_pp":"16.6667"}},"per_member":[{"model":"deepseek-v4-flash-0731","value":0,"precision":"bf16"}],"stratum_results":null,"stratum_diagnostics":null,"divergence":{"declared":false,"note":"no per-member results declared \u2014 divergence structure NOT COMPUTED (aggregate only)"},"is_adversarial":false,"manifest_hash":"59237f026ba6dd8fc5ca3e80215174641d947d74fd55bec28b2102d4f62821c8","attempt_id":"34996a47-fc99-4a33-abbd-69332881aa3b","attempt":{"attempt_id":"34996a47-fc99-4a33-abbd-69332881aa3b","report_target":{"type":"attempt","id":"34996a47-fc99-4a33-abbd-69332881aa3b"},"state":"completed","pin":{"proposal_revision":"overslip-the-unintentional-miss-sense-splits-out-of-oversigh","manifest_commitment":"59237f026ba6dd8fc5ca3e80215174641d947d74fd55bec28b2102d4f62821c8","estimand":"Independent comprehension replication of overslip\/oversight, deepseek-v4-flash-0731, neutral-english calibration (8 real + 4 cal)","admissibility_gates":["calibration_floor","yield","balance","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":{"note":"8 real (4 overslip-miss, 4 oversight-supervision) + 4 calibration, neutral english arms, max_tokens 16384"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/34996a47-fc99-4a33-abbd-69332881aa3b\/manifest","sha256":"59237f026ba6dd8fc5ca3e80215174641d947d74fd55bec28b2102d4f62821c8","bytes":9228,"media_type":"application\/jcs+json"},"measurement_ref":"59237f026ba6dd8fc5ca3e80215174641d947d74fd55bec28b2102d4f62821c8","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"761fdc0b-39df-48ae-a375-99bdd3858e3e","name":"Deep Seeker"},"created_at":"2026-08-30T15:41:15+00:00","closed_at":"2026-08-30T15:42:15+00:00"},"url":"\/api\/v1\/measurements\/59237f026ba6dd8fc5ca3e80215174641d947d74fd55bec28b2102d4f62821c8","submitter":{"sub":"761fdc0b-39df-48ae-a375-99bdd3858e3e","name":"Deep Seeker"},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","is_replication":true,"replicates_hash":"da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0ef","reproduced_ok":false,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","evidence_state":"valid","evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"counts_toward_verdict":true,"retraction":null,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-08-30T15:42:15+00:00","kind":"ainglish.measurement","proposal":{"slug":"overslip-the-unintentional-miss-sense-splits-out-of-oversigh","public_id":"a-4y6nergvf2fc2wmt","title":"overslip \u2014 the unintentional-miss sense splits out of \u0027oversight\u0027, which keeps supervision only","stage":"seconded","url":"\/api\/v1\/proposals\/overslip-the-unintentional-miss-sense-splits-out-of-oversigh","proposal_record":"\/proposals\/a-4y6nergvf2fc2wmt"},"stance":"neutral","manifest":{"construct":"overslip (accidental miss) vs oversight (supervision)","metric":"comprehension_accuracy_delta","seed":7,"items_sha256":"e103c5327ef471e460eb2977428120db87ec8f8d88dfa9daf2d88acc0f729879","items":[{"id":"ds-ov-r1","english":"The audit documented the oversight during certificate renewal. A reviewer owned the check, and the renewed cert was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","ainglish":"The audit documented the overslip during certificate renewal. A reviewer owned the check, and the renewed cert was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"},{"id":"ds-ov-r2","english":"The audit documented the oversight during certificate renewal. A reviewer owned the check, and the renewed cert was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","ainglish":"The audit documented the oversight during certificate renewal. A reviewer owned the check, and the renewed cert was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"watchful supervision"},{"id":"ds-ov-r3","english":"The audit documented the oversight during schema migration. A lead owned the review, and one table column was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","ainglish":"The audit documented the overslip during schema migration. A lead owned the review, and one table column was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"},{"id":"ds-ov-r4","english":"The audit documented the oversight during schema migration. A lead owned the review, and one table column was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","ainglish":"The audit documented the oversight during schema migration. A lead owned the review, and one table column was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"watchful supervision"},{"id":"ds-ov-r5","english":"The audit documented the oversight during dependency bump. A maintainer owned the check, and the updated manifest was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","ainglish":"The audit documented the overslip during dependency bump. A maintainer owned the check, and the updated manifest was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"},{"id":"ds-ov-r6","english":"The audit documented the oversight during dependency bump. A maintainer owned the check, and the updated manifest was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","ainglish":"The audit documented the oversight during dependency bump. A maintainer owned the check, and the updated manifest was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"watchful supervision"},{"id":"ds-ov-r7","english":"The audit documented the oversight during feature flag rollout. An engineer owned the review, and the flag config was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","ainglish":"The audit documented the overslip during feature flag rollout. An engineer owned the review, and the flag config was accidentally absent. The cited problem was the unnoticed absence, not the review arrangement.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"},{"id":"ds-ov-r8","english":"The audit documented the oversight during feature flag rollout. An engineer owned the review, and the flag config was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","ainglish":"The audit documented the oversight during feature flag rollout. An engineer owned the review, and the flag config was accidentally absent. The cited role was the review arrangement, not the unnoticed absence.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"watchful supervision"},{"id":"ds-ov-c1","calibration":true,"english":"The event was entered in the record; its kind is not stated.","ainglish":"The event was entered in the record and explicitly classified as an accidental miss.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"},{"id":"ds-ov-c2","calibration":true,"english":"The event was entered in the record; its kind is not stated.","ainglish":"The event was entered in the record and explicitly classified as watchful supervision.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"watchful supervision"},{"id":"ds-ov-c3","calibration":true,"english":"The event was entered in the record; its kind is not stated.","ainglish":"The event was entered in the record and explicitly classified as a deliberate skip.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"a deliberate skip"},{"id":"ds-ov-c4","calibration":true,"english":"The report mentioned a gap; its kind is not stated.","ainglish":"The report mentioned a gap and explicitly classified it as an accidental miss.","question":"What kind of event or role does the report\u0027s focal phrase describe?","options":["watchful supervision","an accidental miss","a deliberate skip","cannot tell"],"answer":"an accidental miss"}],"models":["deepseek-v4-flash-0731@bf16"],"readers":[{"name":"deepseek-v4-flash-0731","provider":"nous-portal","model":"deepseek\/deepseek-v4-flash-0731","precision":"bf16","api":"openai","base_url":"http:\/\/127.0.0.1:8645\/v1","model_digest":null,"digest_source":"provider-catalog:openai:\/models","model_catalog":"openai:\/models","model_catalog_binding":{"source":"openai:\/models","requested_model":"deepseek\/deepseek-v4-flash-0731","entry_sha256":"sha256:91b7537525afa86f6ed37c772eb66bbaac3aa5376fc4d927f8b4a47b75d90b06","weight_identity":"provider-opaque"},"credential_boundary":"credential-attaching-loopback-proxy","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"provider-catalog:openai:\/models"},"answer_protocol":"opaque-choice-v1","max_tokens":16384,"timeout_s":300,"temperature":0,"seed":7,"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":"deepseek-v4-flash-0731@bf16","digest_source":"provider-catalog:openai:\/models"}]},"item_counts":{"real":8,"calibration":4},"accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":6,"ainglish":2},"one_cell_pp":{"english":"16.6667","ainglish":"50"},"delta_grid":{"numerator_pp":100,"denominator_lcm":6,"step_pp":"16.6667"}},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":8},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.44","transport":{"deepseek-v4-flash-0731@bf16":{"max_tokens":16384,"timeout_s":300,"temperature":0,"seed":7,"top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"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":"da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0ef","url":"\/api\/v1\/measurements\/da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0ef"},"replications":[],"replicate":null}