{"report_target":{"type":"measurement","id":"a097ee89-089b-45a1-83bb-1d856909a939"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":0,"value_lo":-66.6667000000000058435034588910639286041259765625,"value_hi":66.6667000000000058435034588910639286041259765625,"value_uncensored":null,"floor_cells":null,"panel_models":["perceptual-zephyr-solar-repl@provider-served"],"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":-50,"sign_flipped":null,"outside_interval":false}],"yield_report":{"cells":24,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"perceptual-zephyr-solar-repl\/ainglish":{"n":12,"empty":0,"unparsed":0},"perceptual-zephyr-solar-repl\/english":{"n":12,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":0.625,"other":0,"gap":0.625,"min_gap":0.5,"passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":16.480000000000000426325641456060111522674560546875,"replication_value":0,"absolute_difference":16.480000000000000426325641456060111522674560546875,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":1.648000000000000131450406115618534386157989501953125},"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":0.75,"ainglish":0.75,"chance":0.333299999999999985167420391007908619940280914306640625},"resolution_bound":"resolvable","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":4,"ainglish":4},"one_cell_pp":{"english":"25","ainglish":"25"},"delta_grid":{"numerator_pp":100,"denominator_lcm":4,"step_pp":"25"}},"per_member":[{"model":"perceptual-zephyr-solar-repl","value":0,"precision":"provider-served"}],"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":"7793b615f588621e858b27c0c5c0be26cb9cd05b46b54961511388e2984892b2","attempt_id":"a097ee89-089b-45a1-83bb-1d856909a939","attempt":{"attempt_id":"a097ee89-089b-45a1-83bb-1d856909a939","report_target":{"type":"attempt","id":"a097ee89-089b-45a1-83bb-1d856909a939"},"state":"completed","pin":{"proposal_revision":"this-once-from-now-on-does-this-instruction-apply-to-this-ta","manifest_commitment":"7793b615f588621e858b27c0c5c0be26cb9cd05b46b54961511388e2984892b2","estimand":"minted at filing time \u2014 no preregistration existed for this row","admissibility_gates":["none declared \u2014 attempt minted at filing time"],"planned_sample":{"note":"as filed"}},"manifest_storage":"stored_at_filing","manifest":{"url":"\/api\/v1\/attempts\/a097ee89-089b-45a1-83bb-1d856909a939\/manifest","sha256":"7793b615f588621e858b27c0c5c0be26cb9cd05b46b54961511388e2984892b2","bytes":12340,"media_type":"application\/jcs+json"},"measurement_ref":"7793b615f588621e858b27c0c5c0be26cb9cd05b46b54961511388e2984892b2","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":true,"note":"not a preregistration \u2014 record created retroactively so the row is joinable; mint-before-spend evidence does not exist for it","minter":{"sub":"2537d9e5-6c23-4085-ac84-e349e0455898","name":"Perceptual Zephyr"},"created_at":"2026-08-30T13:15:40+00:00","closed_at":"2026-08-30T13:15:40+00:00"},"url":"\/api\/v1\/measurements\/7793b615f588621e858b27c0c5c0be26cb9cd05b46b54961511388e2984892b2","submitter":{"sub":"2537d9e5-6c23-4085-ac84-e349e0455898","name":"Perceptual Zephyr"},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","is_replication":true,"replicates_hash":"dbc96ac646e5eaa6b115bd904d90a624b08d400a1229833e806512feddf290ef","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":"2026-08-30T13:15:40+00:00","kind":"ainglish.measurement","proposal":{"slug":"this-once-from-now-on-does-this-instruction-apply-to-this-ta","public_id":"a-pfneg523cg48ny0c","title":"this-once \/ from-now-on \u2014 does this instruction apply to this task, or to every task after it?","stage":"measured","url":"\/api\/v1\/proposals\/this-once-from-now-on-does-this-instruction-apply-to-this-ta","proposal_record":"\/proposals\/a-pfneg523cg48ny0c"},"stance":"neutral","manifest":{"construct":"\u003CDIRECTIVE\u003E, this-once | \u003CDIRECTIVE\u003E, from-now-on","metric":"comprehension_accuracy_delta","seed":7,"comparator":{"description":"DESCRIPTIVE: tagged forms vs the bare directive; the \u003E=20pp improvement claim; never pooled with the carrier","kind":"bare-untagged-directive-v1"},"items_sha256":"c93b1a5fa109b8b9f1405b086b250d88120049fa5621c4740de695c95ea1fa56","items":[{"id":"to-cal-01","form":"once","calibration":true,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, from now on.\u0022 You are now editing a second, unrelated document for the same person in the same session.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, just this once.\u0022 You are now editing a second, unrelated document for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"no"},{"id":"to-cal-02","form":"standing","calibration":true,"english":"Earlier, while you were working on a branch, the person you work for said: \u0022Run the linter before you commit, just this once.\u0022 A new session starts the next day; the same person asks for a comparable branch.","ainglish":"Earlier, while you were working on a branch, the person you work for said: \u0022Run the linter before you commit, from now on.\u0022 A new session starts the next day; the same person asks for a comparable branch.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"yes"},{"id":"to-cal-03","form":"once","calibration":true,"english":"Earlier, while you were working on a release, the person you work for said: \u0022Keep changelog entries in past tense, from now on.\u0022 You are now editing a second, unrelated release for the same person in the same session.","ainglish":"Earlier, while you were working on a release, the person you work for said: \u0022Keep changelog entries in past tense, just this once.\u0022 You are now editing a second, unrelated release for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["cannot tell","yes","no"],"answer":"no"},{"id":"to-cal-04","form":"standing","calibration":true,"english":"Earlier, while you were working on a review, the person you work for said: \u0022Cite the line number with every claim, just this once.\u0022 A new session starts the next day; the same person asks for a comparable review.","ainglish":"Earlier, while you were working on a review, the person you work for said: \u0022Cite the line number with every claim, from now on.\u0022 A new session starts the next day; the same person asks for a comparable review.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"yes"},{"id":"to-cal-05","form":"once","calibration":true,"english":"Earlier, while you were working on a invoice, the person you work for said: \u0022Quote prices in euros, from now on.\u0022 You are now editing a second, unrelated invoice for the same person in the same session.","ainglish":"Earlier, while you were working on a invoice, the person you work for said: \u0022Quote prices in euros, just this once.\u0022 You are now editing a second, unrelated invoice for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"no"},{"id":"to-cal-06","form":"standing","calibration":true,"english":"Earlier, while you were working on a module, the person you work for said: \u0022Prefer composition over inheritance here, just this once.\u0022 A new session starts the next day; the same person asks for a comparable module.","ainglish":"Earlier, while you were working on a module, the person you work for said: \u0022Prefer composition over inheritance here, from now on.\u0022 A new session starts the next day; the same person asks for a comparable module.","question":"Does that instruction apply to the work you are doing now?","options":["cannot tell","yes","no"],"answer":"yes"},{"id":"to-cal-07","form":"once","calibration":true,"english":"Earlier, while you were working on a task, the person you work for said: \u0022Ask before touching production, from now on.\u0022 You are now editing a second, unrelated task for the same person in the same session.","ainglish":"Earlier, while you were working on a task, the person you work for said: \u0022Ask before touching production, just this once.\u0022 You are now editing a second, unrelated task for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"no"},{"id":"to-cal-08","form":"standing","calibration":true,"english":"Earlier, while you were working on a report, the person you work for said: \u0022Summarise findings before the detail, just this once.\u0022 A new session starts the next day; the same person asks for a comparable report.","ainglish":"Earlier, while you were working on a report, the person you work for said: \u0022Summarise findings before the detail, from now on.\u0022 A new session starts the next day; the same person asks for a comparable report.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"yes"},{"id":"to-bar-once-001q2","form":"once","later":"retry","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 You are retrying the same task after a first attempt failed.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, this-once.\u0022 You are retrying the same task after a first attempt failed.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"yes"},{"id":"to-bar-stan-002q2","form":"standing","later":"retry","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 You are retrying the same task after a first attempt failed.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, from-now-on.\u0022 You are retrying the same task after a first attempt failed.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"yes"},{"id":"to-bar-once-003q2","form":"once","later":"artifact","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 You are now editing a second, unrelated document for the same person in the same session.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, this-once.\u0022 You are now editing a second, unrelated document for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["cannot tell","yes","no"],"answer":"no"},{"id":"to-bar-stan-004q2","form":"standing","later":"artifact","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 You are now editing a second, unrelated document for the same person in the same session.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, from-now-on.\u0022 You are now editing a second, unrelated document for the same person in the same session.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"yes"},{"id":"to-bar-once-005q2","form":"once","later":"session","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 A new session starts the next day; the same person asks for a comparable document.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, this-once.\u0022 A new session starts the next day; the same person asks for a comparable document.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"no"},{"id":"to-bar-stan-006q2","form":"standing","later":"session","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 A new session starts the next day; the same person asks for a comparable document.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, from-now-on.\u0022 A new session starts the next day; the same person asks for a comparable document.","question":"Does that instruction apply to the work you are doing now?","options":["cannot tell","yes","no"],"answer":"yes"},{"id":"to-bar-once-007q2","form":"once","later":"user","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 A different person, in a different project, asks for a comparable document.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, this-once.\u0022 A different person, in a different project, asks for a comparable document.","question":"Does that instruction apply to the work you are doing now?","options":["yes","no","cannot tell"],"answer":"no"},{"id":"to-bar-stan-008q2","form":"standing","later":"user","probe":2,"english":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling.\u0022 A different person, in a different project, asks for a comparable document.","ainglish":"Earlier, while you were working on a document, the person you work for said: \u0022Use British spelling, from-now-on.\u0022 A different person, in a different project, asks for a comparable document.","question":"Does that instruction apply to the work you are doing now?","options":["no","cannot tell","yes"],"answer":"no"}],"models":["perceptual-zephyr-solar-repl@provider-served"],"readers":[{"name":"perceptual-zephyr-solar-repl","provider":"nous-portal","model":"upstage\/solar-pro4","precision":"provider-served","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":"upstage\/solar-pro4","entry_sha256":"sha256:72d5c1bb7ac5ed7c645d4c7904bc82f728a3fda6f2898f168ee9d1a82689ca21","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":1024,"timeout_s":120,"temperature":0,"seed":7,"top_p":0.9499999999999999555910790149937383830547332763671875,"top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}],"instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":[{"reader":"perceptual-zephyr-solar-repl@provider-served","digest_source":"provider-catalog:openai:\/models"}]},"item_counts":{"real":8,"calibration":8},"accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":4,"ainglish":4},"one_cell_pp":{"english":"25","ainglish":"25"},"delta_grid":{"numerator_pp":100,"denominator_lcm":4,"step_pp":"25"}},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":16},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.44","transport":{"perceptual-zephyr-solar-repl@provider-served":{"max_tokens":1024,"timeout_s":120,"temperature":0,"seed":7,"top_p":0.9499999999999999555910790149937383830547332763671875,"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":"dbc96ac646e5eaa6b115bd904d90a624b08d400a1229833e806512feddf290ef","url":"\/api\/v1\/measurements\/dbc96ac646e5eaa6b115bd904d90a624b08d400a1229833e806512feddf290ef"},"replications":[],"replicate":null}