{"report_target":{"type":"measurement","id":"aa619c54-3208-4ffd-9742-451acd2f94ea"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-25,"value_lo":-75,"value_hi":0,"value_uncensored":null,"floor_cells":null,"panel_models":["spark-zen-13-minimal"],"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":-33.3299999999999982946974341757595539093017578125,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":4,"value":0,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":16,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"spark-zen-13-minimal\/ainglish":{"n":8,"empty":0,"unparsed":0},"spark-zen-13-minimal\/english":{"n":8,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0.5,"gap":0.5,"headroom":0.5,"recovered":1,"min_gap":0.125,"min_recovered":0.5,"rule":"headroom-relative-v1","passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":0,"replication_value":-25,"absolute_difference":25,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":0.0200000000000000004163336342344337026588618755340576171875},"roster_changed":true,"shared_members":[],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","commensurability":{"verdict":"point_fallback","rule_version":"0fa4ffa41d5ac6ff70ba64fd2f26e9ad8657fe1d6b2a2439bd4d20411195010f","keys":{"formula_version":{"original":2,"replication":2,"gates":false,"reason":"formula_version_unequal"},"unit":{"original":null,"replication":null,"gates":false,"reason":"unit_declared_one_sided"},"interval_kind":{"original":"undetermined","replication":"bootstrap_items","declared_original":null,"declared_replication":"bootstrap_items","derived":true,"gates":false,"reason":"interval_kind_conflict"},"declared_kind_original":{"original":null,"replication":"undetermined","gates":false,"reason":"declared_kind_conflicts_derived_original"},"declared_kind_replication":{"original":"bootstrap_items","replication":"bootstrap_items","gates":false,"reason":"declared_kind_conflicts_derived_replication"},"estimand_digest":{"original":null,"replication":null,"gates":false,"differs":false,"reason":"estimand_digest_differs"}},"held_on":[],"non_operative_facts":[]},"comparison_identity":{"state":"undeclared","original":null,"replication":null},"unpinned":true,"rule_applied":"point-relative-v1","unpinned_rule":"inert","governance_effect":"eligible_disagreement","settlement_withheld":false},"tokenizer_provenance":null,"input_disjointness":1,"arms":{"english":1,"ainglish":0.75,"chance":0.5},"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"}},"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"ebe7672316de7967392b17501eefb3885e7af546b5f4489453b1ff22979c98ba","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":1987,"items":8,"readers":1,"cells":8},"per_member":[{"model":"spark-zen-13-minimal","value":-25}],"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":"89a9557e4bc4d9928cefeb7ee9114821e7228cb557099e1b0a5a7a9e27408f3d","attempt_id":"aa619c54-3208-4ffd-9742-451acd2f94ea","attempt":{"attempt_id":"aa619c54-3208-4ffd-9742-451acd2f94ea","report_target":{"type":"attempt","id":"aa619c54-3208-4ffd-9742-451acd2f94ea"},"state":"completed","pin":{"proposal_revision":"each-group-group-set-ref-clause-groups-combined-group-set","manifest_commitment":"89a9557e4bc4d9928cefeb7ee9114821e7228cb557099e1b0a5a7a9e27408f3d","estimand":"comprehension_accuracy_delta for each-group\/group-set vs careful English; population: 12 fresh items (4 cal crossed + 8 real), Spark 1.3 single-reader replication of 92d85061 (awaiting settlement 0; compact subset)","admissibility_gates":["every reader returns a live answer","calibration gate passes"],"planned_sample":{"items":12,"readers":1,"cells":24}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/aa619c54-3208-4ffd-9742-451acd2f94ea\/manifest","sha256":"89a9557e4bc4d9928cefeb7ee9114821e7228cb557099e1b0a5a7a9e27408f3d","bytes":5588,"media_type":"application\/jcs+json"},"measurement_ref":"89a9557e4bc4d9928cefeb7ee9114821e7228cb557099e1b0a5a7a9e27408f3d","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"fed5c864-1663-48ae-953a-9b1b4db56413","name":""},"created_at":"2026-09-03T12:15:38+00:00","closed_at":"2026-09-03T12:16:42+00:00"},"url":"\/api\/v1\/measurements\/89a9557e4bc4d9928cefeb7ee9114821e7228cb557099e1b0a5a7a9e27408f3d","submitter":{"sub":"fed5c864-1663-48ae-953a-9b1b4db56413","name":null},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","proposer_at_submission":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","basis":"stamped_at_submission"},"is_replication":true,"replicates_hash":"92d85061748d813965520e6be3f6e57e1c8549fe65d98f2407f86c94b565e293","reproduced_ok":false,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","evidence_state":"valid","evidence_reason_code":null,"evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"evidence_successor_attempt_id":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":"2026-09-03T12:16:42+00:00","kind":"ainglish.measurement","proposal":{"slug":"each-group-group-set-ref-clause-groups-combined-group-set","public_id":"a-4fsc7etzs8ctsjwp","title":"each-group \/ groups-combined \u2014 did the result hold in every group, or only after pooling them?","stage":"seconded","url":"\/api\/v1\/proposals\/each-group-group-set-ref-clause-groups-combined-group-set","proposal_record":"\/proposals\/a-4fsc7etzs8ctsjwp"},"stance":"neutral","manifest":{"construct":"each-group \/ group-set \u2014 ref clause: groups-combined group set","metric":"comprehension_accuracy_delta","seed":5,"comparator":{"kind":"complete-careful-english-v1","description":"Complete careful-English expansion."},"items_sha256":"30dce11048043ea9b4436f3183b80cf17b3ad015e33a232beb5ef6733e40d75c","items":[{"id":"cal-01","calibration":true,"calibration_construct":"group-reference","english":"Each crew must publish the notice.","ainglish":"each-group(crew): publish(notice).","question":"Who must publish the notice?","options":["each crew","the crew set"],"answer":"each crew"},{"id":"cal-02","calibration":true,"calibration_construct":"group-reference","english":"Each crew must publish the notice.","ainglish":"group-set(crew): publish(notice).","question":"Who must publish the notice?","options":["each crew","the crew set"],"answer":"the crew set"},{"id":"cal-03","calibration":true,"calibration_construct":"group-reference","english":"The crew set must publish the notice.","ainglish":"each-group(crew): publish(notice).","question":"Who must publish the notice?","options":["each crew","the crew set"],"answer":"each crew"},{"id":"cal-04","calibration":true,"calibration_construct":"group-reference","english":"The crew set must publish the notice.","ainglish":"group-set(crew): publish(notice).","question":"Who must publish the notice?","options":["each crew","the crew set"],"answer":"the crew set"},{"id":"real-01","calibration":false,"english":"Each unit must audit the ledger.","ainglish":"each-group(unit): audit(ledger).","question":"Who must audit the ledger?","options":["each unit","the unit set"],"answer":"each unit"},{"id":"real-01b","calibration":false,"english":"The unit set must audit the ledger.","ainglish":"group-set(unit): audit(ledger).","question":"Who must audit the ledger?","options":["the unit set","each unit"],"answer":"the unit set"},{"id":"real-02","calibration":false,"english":"Each squad must inspect the inventory.","ainglish":"each-group(squad): inspect(inventory).","question":"Who must inspect the inventory?","options":["the squad set","each squad"],"answer":"each squad"},{"id":"real-02b","calibration":false,"english":"The squad set must inspect the inventory.","ainglish":"group-set(squad): inspect(inventory).","question":"Who must inspect the inventory?","options":["each squad","the squad set"],"answer":"the squad set"},{"id":"real-03","calibration":false,"english":"Each panel must sign the charter.","ainglish":"each-group(panel): sign(charter).","question":"Who must sign the charter?","options":["each panel","the panel set"],"answer":"each panel"},{"id":"real-03b","calibration":false,"english":"The panel set must sign the charter.","ainglish":"group-set(panel): sign(charter).","question":"Who must sign the charter?","options":["each panel","the panel set"],"answer":"the panel set"},{"id":"real-04","calibration":false,"english":"Each shift must file the docket.","ainglish":"each-group(shift): file(docket).","question":"Who must file the docket?","options":["the shift set","each shift"],"answer":"each shift"},{"id":"real-04b","calibration":false,"english":"The shift set must file the docket.","ainglish":"group-set(shift): file(docket).","question":"Who must file the docket?","options":["each shift","the shift set"],"answer":"the shift set"}],"models":["spark-zen-13-minimal"],"readers":[{"name":"spark-zen-13-minimal","provider":"opencode-zen","model":"muse-spark-1.3-contributor-free","api":"responses","base_url":"https:\/\/opencode.ai\/zen\/v1","model_digest":null,"digest_source":"provider-opaque","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"provider-opaque"},"answer_protocol":"opaque-choice-v1","max_tokens":1024,"timeout_s":120,"temperature":null,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"minimal"}],"instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":[{"reader":"spark-zen-13-minimal","digest_source":"provider-opaque"}]},"item_counts":{"real":8,"calibration":4},"interval_kind":"bootstrap_items","interval_estimator":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","algorithm":"sha256-counter-modulo-v1","draws":2000,"sampling_unit":"item","quantiles":["0.025","0.975"],"items_index_sha256":"66f4918fb213d684411913e28c2fbf91355d2dbcafc4b487d161debda91c5941"},"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":0.125,"min_recovered":0.5,"rule":"headroom-relative-v1","ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":8},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.51","transport":{"spark-zen-13-minimal":{"max_tokens":1024,"timeout_s":120,"temperature":null,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"minimal"}},"concurrency":{"max_in_flight":1,"per_reader_max_in_flight":{"spark-zen-13-minimal":1},"result_order":"deterministic-plan-order","calibration_barrier":true,"automatic_retries":false},"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"},"interval_provenance_attestation":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","metric":"comprehension_accuracy_delta","estimator":"arm_accuracy_delta_pp","algorithm":{"name":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":1987,"sampling_unit":"item","lower_quantile":{"numerator":25,"denominator":1000,"index_rule":"floor"},"upper_quantile":{"numerator":975,"denominator":1000,"index_rule":"floor"}},"seed":5,"items":[{"id":"real-01"},{"id":"real-01b"},{"id":"real-02"},{"id":"real-02b"},{"id":"real-03"},{"id":"real-03b"},{"id":"real-04"},{"id":"real-04b"}],"readers":["spark-zen-13-minimal"],"cells":[{"item_id":"real-01","reader":"spark-zen-13-minimal","arm":"ainglish","correct":false},{"item_id":"real-01b","reader":"spark-zen-13-minimal","arm":"english","correct":true},{"item_id":"real-02","reader":"spark-zen-13-minimal","arm":"english","correct":true},{"item_id":"real-02b","reader":"spark-zen-13-minimal","arm":"ainglish","correct":true},{"item_id":"real-03","reader":"spark-zen-13-minimal","arm":"english","correct":true},{"item_id":"real-03b","reader":"spark-zen-13-minimal","arm":"ainglish","correct":true},{"item_id":"real-04","reader":"spark-zen-13-minimal","arm":"english","correct":true},{"item_id":"real-04b","reader":"spark-zen-13-minimal","arm":"ainglish","correct":true}],"content_sha256":"ebe7672316de7967392b17501eefb3885e7af546b5f4489453b1ff22979c98ba"},"replicates":{"hash":"92d85061748d813965520e6be3f6e57e1c8549fe65d98f2407f86c94b565e293","url":"\/api\/v1\/measurements\/92d85061748d813965520e6be3f6e57e1c8549fe65d98f2407f86c94b565e293"},"replications":[],"replicate":null}