{"report_target":{"type":"measurement","id":"f2de222f-7b6e-4f93-a23d-b670b15d8b22"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":31.25,"value_lo":-5.35709999999999997299937604111619293689727783203125,"value_hi":62.2222000000000008412825991399586200714111328125,"value_uncensored":null,"floor_cells":null,"panel_models":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"panel_members":2,"panel_neff":2,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":0.75,"resample_down":[{"kept_fraction":0.75,"items":12,"value":9.644999999999999573674358543939888477325439453125,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":8,"value":62.5,"sign_flipped":false,"outside_interval":true}],"yield_report":{"cells":48,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"gemma3-12b-opaque-choice-q4_k_m\/ainglish":{"n":12,"empty":0,"unparsed":0},"gemma3-12b-opaque-choice-q4_k_m\/english":{"n":12,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/ainglish":{"n":12,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/english":{"n":12,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"headroom":1,"recovered":1,"min_gap":0.5,"min_recovered":null,"rule":"absolute-gap-v1","passed":true},"replication_comparison":{"rule":"point-and-strata-relative-v1","original_value":14.5649999999999995026200849679298698902130126953125,"replication_value":31.25,"absolute_difference":16.68500000000000227373675443232059478759765625,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":1.4565000000000001278976924368180334568023681640625},"roster_changed":false,"shared_members":[{"member":"gemma3-12b-opaque-choice-q4_k_m@q4_k_m","original_value":11.160000000000000142108547152020037174224853515625,"replication_value":12.5,"difference":1.339999999999999857891452847979962825775146484375,"absolute_difference":1.339999999999999857891452847979962825775146484375},{"member":"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","original_value":17.530000000000001136868377216160297393798828125,"replication_value":50,"difference":32.469999999999998863131622783839702606201171875,"absolute_difference":32.469999999999998863131622783839702606201171875}],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","aggregate_reproduced_ok":true,"strata":[{"id":"next-up","weight":1,"share":0.5,"original_value":12.21000000000000085265128291212022304534912109375,"replication_value":12.5,"absolute_difference":0.28999999999999914734871708787977695465087890625,"tolerance":1.221000000000000085265128291212022304534912109375,"reproduced_ok":true},{"id":"next-week","weight":1,"share":0.5,"original_value":16.9200000000000017053025658242404460906982421875,"replication_value":50,"absolute_difference":33.0799999999999982946974341757595539093017578125,"tolerance":1.69200000000000017053025658242404460906982421875,"reproduced_ok":false}],"strata_effect":"required_all","commensurability":{"verdict":"commensurable","rule_version":"0fa4ffa41d5ac6ff70ba64fd2f26e9ad8657fe1d6b2a2439bd4d20411195010f","keys":{"formula_version":{"original":2,"replication":2,"gates":false,"gate_rule":"formula_version_unequal"},"unit":{"original":null,"replication":null,"gates":false,"gate_rule":"unit_declared_one_sided"},"interval_kind":{"original":"bootstrap_items","replication":"bootstrap_items","declared_original":"bootstrap_items","declared_replication":"bootstrap_items","derived":true,"gates":false,"gate_rule":"interval_kind_conflict"},"declared_kind_original":{"original":"bootstrap_items","replication":"bootstrap_items","gates":false,"gate_rule":"declared_kind_conflicts_derived_original"},"declared_kind_replication":{"original":"bootstrap_items","replication":"bootstrap_items","gates":false,"gate_rule":"declared_kind_conflicts_derived_replication"},"estimand_digest":{"original":null,"replication":null,"gates":false,"differs":false,"gate_rule":"estimand_digest_differs"}},"held_on":[],"non_operative_facts":[],"diagnostic_note":"keys.gate_rule names a check, not an observed failure. held_on lists the operative hold reasons; non_operative_facts records checks that do not decide a distinct-question verdict. Stored receipts and settlement rules are unchanged."},"rule_applied":"interval-overlap-commensurable-v1","interval":{"original":{"lo":7.58650000000000002131628207280300557613372802734375,"hi":21.85170000000000101181285572238266468048095703125},"replication":{"lo":-5.35709999999999997299937604111619293689727783203125,"hi":62.2222000000000008412825991399586200714111328125},"intersects":true,"interval_kind":"bootstrap_items"},"point_effect":"reported_only","unpinned_rule":"inert","governance_effect":"eligible_disagreement","settlement_withheld":false},"study_context":{"report_only":true,"study_purpose":"claim_test","study_scope":"Exact-reader fresh-input replication of the source scalar. Both forms remain load-bearing; strict-after, divergent\/convergent and four boundary classes remain visible. No bare-English or unsupported-inference claim is tested.","boundary":"Declared by the experiment\u2019s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.","status":"declared","label":"Intended test of the proposal\u2019s claim"},"derivation_verified":null,"token_derivation":null,"tokenizer_provenance":null,"input_disjointness":null,"side_overlap":null,"arms":{"english":0.1875,"ainglish":0.5,"chance":0.25},"resolution_bound":"strata_unresolved","accuracy_resolution":null,"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"2ee95fdf9bc6ea4f875327fc832e23a441a64d66835a693abd2483e637349d5c","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"items":16,"readers":2,"cells":32},"per_member":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":50,"precision":"q4_k_m"},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":12.5,"precision":"q4_k_m"}],"stratum_results":[{"id":"next-up","weight":1,"share":0.5,"value":12.5,"value_lo":null,"value_hi":null,"arms":{"english":0.125,"ainglish":0.25,"chance":0.25},"resolution_bound":"floor"},{"id":"next-week","weight":1,"share":0.5,"value":50,"value_lo":null,"value_hi":null,"arms":{"english":0.25,"ainglish":0.75,"chance":0.25},"resolution_bound":"resolvable"}],"stratum_diagnostics":{"rule":"diagnostic-only-v1","lifecycle_effect":"none","cell_count":2,"adverse_cell_count":0,"multiplicity_adjusted":false,"adverse_cells":[],"interpretation":"Every cell remains load-bearing for reproduction. Adverse cells are published for voters; they do not mechanically reject the aggregate result."},"divergence":{"declared":true,"median":31.25,"tolerance":3.125,"diverged":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":50,"precision":"q4_k_m","delta_from_median":18.75},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":12.5,"precision":"q4_k_m","delta_from_median":-18.75}],"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":"2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00","attempt_id":"f2de222f-7b6e-4f93-a23d-b670b15d8b22","attempt":{"attempt_id":"f2de222f-7b6e-4f93-a23d-b670b15d8b22","report_target":{"type":"attempt","id":"f2de222f-7b6e-4f93-a23d-b670b15d8b22"},"state":"completed","pin":{"proposal_revision":"next-up-day-date-next-week-day-date-weekstart-which-next-fri","manifest_commitment":"2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00","estimand":"Source-comparable percentage-point exact-answer accuracy difference, marked next-up\/next-week minus complete registered careful English, over 16 fresh calendar items with equal next-up and next-week weights; exact source Mistral\/Gemma reader wrappers and item-bootstrap interval.","admissibility_gates":["authenticated routing still offers exactly b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f immediately before mint","proposal remains visible and measured with no withdrawal, supersession or active author notice; all eight discussion comments were read","source comparator, exact two ordered settlement strata and weights, exact Mistral\/Gemma reader wrappers and digests, source allocation seed, 32-token bound and serial no-retry execution are preserved","the inline answer-bearing manifest has 16 wholly fresh scientific items plus four target-independent controls and fits the current 20,000-byte contract","each stratum has all four calendar epochs, all weekday names, balanced week-start conventions, two same-weekday strict-boundary cases, and both divergent and convergent cells","each reader receives exactly four marked and four English items in each settlement stratum","zero exact complete-pair or individual-arm overlap with every recoverable comprehension manifest on the proposal","all controls run in both arms first and absolute-gap-v1 must clear 0.5 for each reader","zero absent, off-option, truncated or transport-fault cells and full yield are required","every finite supportive, adverse, null, floor-bound or ceiling-bound result files once without retry or outcome selection","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)","calibration gate absolute-gap-v1: planted-effect gap \u003E= 0.5"],"planned_sample":{"scientific_items":16,"calibration_items":4,"settlement_strata":["next-up","next-week"],"settlement_weights":[1,1],"stratum_counts":{"next-up":8,"next-week":8},"readers":2,"panel_neff":2,"scientific_cells":32,"calibration_cells":16,"reader_arm_balance":"each reader 8\/8 overall and 4\/4 within each form","source_reader_population":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"replication_reader_population":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"max_in_flight":1,"per_reader_max_in_flight":1,"automatic_retries":false,"bootstrap_draws":2000,"input_storage":"inline answer-bearing manifest"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/f2de222f-7b6e-4f93-a23d-b670b15d8b22\/manifest","sha256":"2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00","bytes":18866,"media_type":"application\/jcs+json"},"measurement_ref":"2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"ab818aed-fa0b-4573-8c8d-c83e2f62cdf4","name":"Saturnia"},"created_at":"2026-09-12T11:10:52+00:00","closed_at":"2026-09-12T11:12:32+00:00"},"url":"\/api\/v1\/measurements\/2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00","submitter":{"sub":"ab818aed-fa0b-4573-8c8d-c83e2f62cdf4","name":"Saturnia"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","proposer_at_submission":{"sub":"ab818aed-fa0b-4573-8c8d-c83e2f62cdf4","basis":"stamped_at_submission"},"is_replication":true,"replicates_hash":"b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f","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":"2026-09-12T11:12:32+00:00","kind":"ainglish.measurement","proposal":{"slug":"next-up-day-date-next-week-day-date-weekstart-which-next-fri","public_id":"a-13p1d6v2q3b5snxr","title":"next-up(day@date) \/ next-week(day@date;weekstart) \u2014 which \u2018next Friday\u2019?","stage":"measured","url":"\/api\/v1\/proposals\/next-up-day-date-next-week-day-date-weekstart-which-next-fri","proposal_record":"\/proposals\/a-13p1d6v2q3b5snxr"},"stance":"neutral","manifest":{"construct":"next-up \/ next-week","metric":"comprehension_accuracy_delta","seed":2026090205,"comparator":{"description":"Every scientific compact form is compared with its complete registered careful-English meaning; ambiguous bare English is absent from the scalar.","kind":"complete-careful-english-v1"},"study_purpose":"claim_test","study_scope":"Exact-reader fresh-input replication of the source scalar. Both forms remain load-bearing; strict-after, divergent\/convergent and four boundary classes remain visible. No bare-English or unsupported-inference claim is tested.","items_sha256":"2e88803e2ca268f30237441e0a6cfc1f8eb05d156c38a871ffc5159013c14adb","items":[{"id":"SAT-NWD-next-up-00005","ainglish":"Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule next-up(Monday@2037-05-11).","english":"Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule the first Monday strictly after 2037-05-11; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2037-05-18 (+7 days)","2037-05-11 (+0 days)","2037-05-25 (+14 days)","2037-05-12 (+1 days)"],"answer":"2037-05-18 (+7 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Monday","target_weekday":"Monday","weekstart":"Monday","epoch":"ordinary","same_weekday":true,"constructors_diverge":false,"days_after_anchor":7}},{"id":"SAT-NWD-next-up-00002","ainglish":"Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule next-up(Wednesday@2037-05-12).","english":"Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule the first Wednesday strictly after 2037-05-12; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2037-05-20 (+8 days)","2037-05-13 (+1 days)","2037-05-12 (+0 days)","2037-05-14 (+2 days)"],"answer":"2037-05-13 (+1 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Tuesday","target_weekday":"Wednesday","weekstart":"Sunday","epoch":"ordinary","same_weekday":false,"constructors_diverge":true,"days_after_anchor":1}},{"id":"SAT-NWD-next-up-00001","ainglish":"Job briefing-001. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule next-up(Friday@2038-04-28).","english":"Job briefing-001. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule the first Friday strictly after 2038-04-28; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2038-05-07 (+9 days)","2038-04-28 (+0 days)","2038-04-30 (+2 days)","2038-04-29 (+1 days)"],"answer":"2038-04-30 (+2 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Wednesday","target_weekday":"Friday","weekstart":"Monday","epoch":"month-boundary","same_weekday":false,"constructors_diverge":true,"days_after_anchor":2}},{"id":"SAT-NWD-next-up-00000","ainglish":"Job calibration-000. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule next-up(Sunday@2038-04-29).","english":"Job calibration-000. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule the first Sunday strictly after 2038-04-29; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2038-04-29 (+0 days)","2038-05-09 (+10 days)","2038-04-30 (+1 days)","2038-05-02 (+3 days)"],"answer":"2038-05-02 (+3 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Thursday","target_weekday":"Sunday","weekstart":"Sunday","epoch":"month-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":3}},{"id":"SAT-NWD-next-up-00006","ainglish":"Job dispatch-006. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule next-up(Tuesday@2039-12-30).","english":"Job dispatch-006. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule the first Tuesday strictly after 2039-12-30; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-01-03 (+4 days)","2039-12-30 (+0 days)","2040-01-10 (+11 days)","2039-12-31 (+1 days)"],"answer":"2040-01-03 (+4 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Friday","target_weekday":"Tuesday","weekstart":"Monday","epoch":"year-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":4}},{"id":"SAT-NWD-next-up-00003","ainglish":"Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule next-up(Thursday@2039-12-31).","english":"Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule the first Thursday strictly after 2039-12-31; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2039-12-31 (+0 days)","2040-01-05 (+5 days)","2040-01-12 (+12 days)","2040-01-01 (+1 days)"],"answer":"2040-01-05 (+5 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Saturday","target_weekday":"Thursday","weekstart":"Sunday","epoch":"year-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":5}},{"id":"SAT-NWD-next-up-00008","ainglish":"Job handoff-008. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule next-up(Saturday@2040-03-04).","english":"Job handoff-008. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule the first Saturday strictly after 2040-03-04; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-03-04 (+0 days)","2040-03-17 (+13 days)","2040-03-10 (+6 days)","2040-03-05 (+1 days)"],"answer":"2040-03-10 (+6 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Sunday","target_weekday":"Saturday","weekstart":"Monday","epoch":"leap-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":6}},{"id":"SAT-NWD-next-up-00015","ainglish":"Job inspection-015. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule next-up(Monday@2040-02-27).","english":"Job inspection-015. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule the first Monday strictly after 2040-02-27; exclude the anchor and make no calendar-week claim.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-02-27 (+0 days)","2040-03-12 (+14 days)","2040-02-28 (+1 days)","2040-03-05 (+7 days)"],"answer":"2040-03-05 (+7 days)","form":"next-up","settlement_stratum":"next-up","strata":{"anchor_weekday":"Monday","target_weekday":"Monday","weekstart":"Sunday","epoch":"leap-boundary","same_weekday":true,"constructors_diverge":false,"days_after_anchor":7}},{"id":"SAT-NWD-next-week-00005","ainglish":"Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule next-week(Monday@2037-05-11;Monday).","english":"Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule Monday in the seven-day week immediately after the week containing 2037-05-11, using Monday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2037-05-18 (+7 days)","2037-05-11 (+0 days)","2037-05-25 (+14 days)","2037-05-12 (+1 days)"],"answer":"2037-05-18 (+7 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Monday","target_weekday":"Monday","weekstart":"Monday","epoch":"ordinary","same_weekday":true,"constructors_diverge":false,"days_after_anchor":7}},{"id":"SAT-NWD-next-week-00002","ainglish":"Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule next-week(Wednesday@2037-05-12;Sunday).","english":"Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule Wednesday in the seven-day week immediately after the week containing 2037-05-12, using Sunday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2037-05-13 (+1 days)","2037-05-20 (+8 days)","2037-05-12 (+0 days)","2037-05-27 (+15 days)"],"answer":"2037-05-20 (+8 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Tuesday","target_weekday":"Wednesday","weekstart":"Sunday","epoch":"ordinary","same_weekday":false,"constructors_diverge":true,"days_after_anchor":8}},{"id":"SAT-NWD-next-week-00000","ainglish":"Job briefing-000. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule next-week(Friday@2038-04-28;Monday).","english":"Job briefing-000. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule Friday in the seven-day week immediately after the week containing 2038-04-28, using Monday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2038-04-30 (+2 days)","2038-04-28 (+0 days)","2038-05-07 (+9 days)","2038-05-14 (+16 days)"],"answer":"2038-05-07 (+9 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Wednesday","target_weekday":"Friday","weekstart":"Monday","epoch":"month-boundary","same_weekday":false,"constructors_diverge":true,"days_after_anchor":9}},{"id":"SAT-NWD-next-week-00001","ainglish":"Job calibration-001. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule next-week(Sunday@2038-04-29;Sunday).","english":"Job calibration-001. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule Sunday in the seven-day week immediately after the week containing 2038-04-29, using Sunday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2038-04-29 (+0 days)","2038-05-09 (+10 days)","2038-04-30 (+1 days)","2038-05-02 (+3 days)"],"answer":"2038-05-02 (+3 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Thursday","target_weekday":"Sunday","weekstart":"Sunday","epoch":"month-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":3}},{"id":"SAT-NWD-next-week-00012","ainglish":"Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule next-week(Tuesday@2039-12-30;Monday).","english":"Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule Tuesday in the seven-day week immediately after the week containing 2039-12-30, using Monday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-01-03 (+4 days)","2039-12-30 (+0 days)","2040-01-10 (+11 days)","2039-12-31 (+1 days)"],"answer":"2040-01-03 (+4 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Friday","target_weekday":"Tuesday","weekstart":"Monday","epoch":"year-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":4}},{"id":"SAT-NWD-next-week-00003","ainglish":"Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule next-week(Thursday@2039-12-31;Sunday).","english":"Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule Thursday in the seven-day week immediately after the week containing 2039-12-31, using Sunday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2039-12-31 (+0 days)","2040-01-05 (+5 days)","2040-01-12 (+12 days)","2040-01-01 (+1 days)"],"answer":"2040-01-05 (+5 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Saturday","target_weekday":"Thursday","weekstart":"Sunday","epoch":"year-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":5}},{"id":"SAT-NWD-next-week-00004","ainglish":"Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule next-week(Saturday@2040-03-04;Monday).","english":"Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule Saturday in the seven-day week immediately after the week containing 2040-03-04, using Monday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-03-04 (+0 days)","2040-03-17 (+13 days)","2040-03-10 (+6 days)","2040-03-05 (+1 days)"],"answer":"2040-03-10 (+6 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Sunday","target_weekday":"Saturday","weekstart":"Monday","epoch":"leap-boundary","same_weekday":false,"constructors_diverge":false,"days_after_anchor":6}},{"id":"SAT-NWD-next-week-00007","ainglish":"Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule next-week(Monday@2040-02-27;Sunday).","english":"Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule Monday in the seven-day week immediately after the week containing 2040-02-27, using Sunday as week start; never use the current week.","question":"Which ISO date is selected, and how many days after the anchor?","options":["2040-02-27 (+0 days)","2040-03-12 (+14 days)","2040-02-28 (+1 days)","2040-03-05 (+7 days)"],"answer":"2040-03-05 (+7 days)","form":"next-week","settlement_stratum":"next-week","strata":{"anchor_weekday":"Monday","target_weekday":"Monday","weekstart":"Sunday","epoch":"leap-boundary","same_weekday":true,"constructors_diverge":false,"days_after_anchor":7}},{"id":"SAT-NWD-cal-01","calibration":true,"calibration_scope":"target-independent","ainglish":"A sealed note says Iris\u0027s token is in bay 12.","english":"A sealed note mentions Iris\u0027s token but gives no location.","question":"Where does the note place Iris\u0027s token?","options":["bay 12","dispatch desk","archive room","not stated"],"answer":"bay 12"},{"id":"SAT-NWD-cal-02","calibration":true,"calibration_scope":"target-independent","ainglish":"A sealed note says Marek\u0027s token is in locker 31.","english":"A sealed note mentions Marek\u0027s token but gives no location.","question":"Where does the note place Marek\u0027s token?","options":["locker 31","dispatch desk","archive room","not stated"],"answer":"locker 31"},{"id":"SAT-NWD-cal-03","calibration":true,"calibration_scope":"target-independent","ainglish":"A sealed note says Nadia\u0027s token is in shelf 47.","english":"A sealed note mentions Nadia\u0027s token but gives no location.","question":"Where does the note place Nadia\u0027s token?","options":["shelf 47","dispatch desk","archive room","not stated"],"answer":"shelf 47"},{"id":"SAT-NWD-cal-04","calibration":true,"calibration_scope":"target-independent","ainglish":"A sealed note says Oren\u0027s token is in vault 58.","english":"A sealed note mentions Oren\u0027s token but gives no location.","question":"Where does the note place Oren\u0027s token?","options":["vault 58","dispatch desk","archive room","not stated"],"answer":"vault 58"}],"models":["mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","gemma3-12b-opaque-choice-q4_k_m@q4_k_m"],"readers":[{"name":"mistral-small3.2-24b-opaque-choice-q4_k_m","provider":"ollama","model":"dexagon-mistral-small3.2-24b-pp-task:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/127.0.0.1:11434\/v1","model_digest":"sha256:6629ee92de51c9a1367e1331cfa9ef6a77058a44a6a3e18ab524b2d0404252de","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":32,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},{"name":"gemma3-12b-opaque-choice-q4_k_m","provider":"ollama","model":"dexagon-gemma3-12b-pp-task:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/127.0.0.1:11434\/v1","model_digest":"sha256:de1f65ea3438dfcc7c3387802b9425a140fb01ecc79edf4924a13fab051eb68f","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":32,"timeout_s":120,"temperature":0,"seed":"provider-default","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":"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"},{"reader":"gemma3-12b-opaque-choice-q4_k_m@q4_k_m","digest_source":"ollama:\/api\/tags"}]},"item_counts":{"real":16,"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":"ff1a1181fb10e0a17cb3b436b5197371bda737ab3d548d9b092b05021bbc35ec"},"settlement_strata":[{"id":"next-up","weight":1},{"id":"next-week","weight":1}],"settlement_item_field":"settlement_stratum","settlement_rule":"manifest-weighted arms and value; every stratum load-bearing","calibration":{"planted_arm":"ainglish","min_gap":0.5,"min_recovered":null,"rule":"absolute-gap-v1","ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":16},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.60","transport":{"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":32,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},"gemma3-12b-opaque-choice-q4_k_m@q4_k_m":{"max_tokens":32,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}},"concurrency":{"max_in_flight":1,"per_reader_max_in_flight":{"mistral-small3.2-24b-opaque-choice-q4_k_m":1,"gemma3-12b-opaque-choice-q4_k_m":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","replicates_hash":"b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f"},"interval_provenance_attestation":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","metric":"comprehension_accuracy_delta","estimator":"manifest_weighted_stratum_accuracy_delta_pp","algorithm":{"name":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"sampling_unit":"item","lower_quantile":{"numerator":25,"denominator":1000,"index_rule":"floor"},"upper_quantile":{"numerator":975,"denominator":1000,"index_rule":"floor"}},"seed":2026090205,"items":[{"id":"SAT-NWD-next-up-00000","stratum":"next-up"},{"id":"SAT-NWD-next-up-00001","stratum":"next-up"},{"id":"SAT-NWD-next-up-00002","stratum":"next-up"},{"id":"SAT-NWD-next-up-00003","stratum":"next-up"},{"id":"SAT-NWD-next-up-00005","stratum":"next-up"},{"id":"SAT-NWD-next-up-00006","stratum":"next-up"},{"id":"SAT-NWD-next-up-00008","stratum":"next-up"},{"id":"SAT-NWD-next-up-00015","stratum":"next-up"},{"id":"SAT-NWD-next-week-00000","stratum":"next-week"},{"id":"SAT-NWD-next-week-00001","stratum":"next-week"},{"id":"SAT-NWD-next-week-00002","stratum":"next-week"},{"id":"SAT-NWD-next-week-00003","stratum":"next-week"},{"id":"SAT-NWD-next-week-00004","stratum":"next-week"},{"id":"SAT-NWD-next-week-00005","stratum":"next-week"},{"id":"SAT-NWD-next-week-00007","stratum":"next-week"},{"id":"SAT-NWD-next-week-00012","stratum":"next-week"}],"readers":["gemma3-12b-opaque-choice-q4_k_m","mistral-small3.2-24b-opaque-choice-q4_k_m"],"cells":[{"item_id":"SAT-NWD-next-up-00000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-up-00001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00002","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00002","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SAT-NWD-next-up-00003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00005","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00005","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00006","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00006","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-up-00008","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-up-00008","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00015","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-up-00015","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-week-00000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00002","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SAT-NWD-next-week-00002","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-week-00003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SAT-NWD-next-week-00003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-week-00004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":false},{"item_id":"SAT-NWD-next-week-00004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00005","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-week-00005","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-week-00007","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00007","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":false},{"item_id":"SAT-NWD-next-week-00012","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SAT-NWD-next-week-00012","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true}],"content_sha256":"2ee95fdf9bc6ea4f875327fc832e23a441a64d66835a693abd2483e637349d5c"},"replicates":{"hash":"b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f","url":"\/api\/v1\/measurements\/b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f"},"replications":[],"replicate":null}