{"report_target":{"type":"measurement","id":"61ca8d8c-c048-4fff-b7e2-c07ef6160c9b"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":50,"value_lo":0,"value_hi":85.7142999999999943838702165521681308746337890625,"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":50,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":4,"value":50,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":16,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"deepseek-v4-flash-0731\/ainglish":{"n":10,"empty":0,"unparsed":0},"deepseek-v4-flash-0731\/english":{"n":6,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":0.5,"other":0,"gap":0.5,"min_gap":0.5,"passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":50,"replication_value":50,"absolute_difference":0,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":5},"roster_changed":true,"shared_members":[],"reproduced_ok":true,"member_diagnostics_effect":"diagnostic_only","governance_effect":"eligible_agreement"},"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":0,"ainglish":0.5,"chance":0.333299999999999985167420391007908619940280914306640625},"resolution_bound":"resolvable","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":2,"ainglish":6},"one_cell_pp":{"english":"50","ainglish":"16.6667"},"delta_grid":{"numerator_pp":100,"denominator_lcm":6,"step_pp":"16.6667"}},"per_member":[{"model":"deepseek-v4-flash-0731","value":50,"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":"239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81","attempt_id":"61ca8d8c-c048-4fff-b7e2-c07ef6160c9b","attempt":{"attempt_id":"61ca8d8c-c048-4fff-b7e2-c07ef6160c9b","report_target":{"type":"attempt","id":"61ca8d8c-c048-4fff-b7e2-c07ef6160c9b"},"state":"completed","pin":{"proposal_revision":"percentage-points-not-percent","manifest_commitment":"239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81","estimand":"Independent comprehension replication of percentage-points-not-percent, deepseek-v4-flash-0731, short-arm 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 additive-points, 4 relative-percent) + 4 calibration, short arms, max_tokens 16384"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/61ca8d8c-c048-4fff-b7e2-c07ef6160c9b\/manifest","sha256":"239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81","bytes":6850,"media_type":"application\/jcs+json"},"measurement_ref":"239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81","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":"2026-08-30T14:24:35+00:00","closed_at":"2026-08-30T14:25:10+00:00"},"url":"\/api\/v1\/measurements\/239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81","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":"4274686df67d83ec8fb12f9468142140564436fb898e65941a8e8ef6c468b559","reproduced_ok":true,"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":"2026-08-30T14:25:10+00:00","kind":"ainglish.measurement","proposal":{"slug":"percentage-points-not-percent","public_id":"a-vdfmetgvbqe4eczj","title":"percentage points, not bare percent \u2014 a change to a percentage is stated in points, endpoints attached when known","stage":"measured","url":"\/api\/v1\/proposals\/percentage-points-not-percent","proposal_record":"\/proposals\/a-vdfmetgvbqe4eczj"},"stance":"neutral","manifest":{"construct":"percentage points, not percent","metric":"comprehension_accuracy_delta","seed":7,"items_sha256":"f4498a250214cb73012b48cddffeba86962bba20ad85b0e0d5f9084b612e4fcc","items":[{"id":"ds-pp-r1","english":"The task success rate changed in the new build.","ainglish":"The task success rate rose 7 percentage points in the new build.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-r2","english":"The task success rate changed in the new build.","ainglish":"The task success rate rose 7% in the new build.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"},{"id":"ds-pp-r3","english":"The request latency changed after the change.","ainglish":"The request latency rose 3 percentage points after the change.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-r4","english":"The request latency changed after the change.","ainglish":"The request latency rose 3% after the change.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"},{"id":"ds-pp-r5","english":"The activation rate changed for the cohort.","ainglish":"The activation rate rose 9 percentage points for the cohort.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-r6","english":"The activation rate changed for the cohort.","ainglish":"The activation rate rose 9% for the cohort.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"},{"id":"ds-pp-r7","english":"The conversion rate changed this quarter.","ainglish":"The conversion rate rose 5 percentage points this quarter.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-r8","english":"The conversion rate changed this quarter.","ainglish":"The conversion rate rose 5% this quarter.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"},{"id":"ds-pp-c1","calibration":true,"english":"The archive acceptance rate changed after the comparison window.","ainglish":"The archive acceptance rate rose 6 percentage points after the comparison window.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-c2","calibration":true,"english":"The archive acceptance rate changed after the comparison window.","ainglish":"The archive acceptance rate rose 6% after the comparison window.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"},{"id":"ds-pp-c3","calibration":true,"english":"The cache hit rate changed over the interval.","ainglish":"The cache hit rate rose 4 percentage points over the interval.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"additive percentage-point change"},{"id":"ds-pp-c4","calibration":true,"english":"The cache hit rate changed over the interval.","ainglish":"The cache hit rate rose 4% over the interval.","question":"Which kind of percentage change did the writer explicitly declare?","options":["cannot tell from the sentence","additive percentage-point change","relative-percent change"],"answer":"relative-percent change"}],"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":2,"ainglish":6},"one_cell_pp":{"english":"50","ainglish":"16.6667"},"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":"4274686df67d83ec8fb12f9468142140564436fb898e65941a8e8ef6c468b559","url":"\/api\/v1\/measurements\/4274686df67d83ec8fb12f9468142140564436fb898e65941a8e8ef6c468b559"},"replications":[],"replicate":null}