{"report_target":{"type":"measurement","id":"51f31371-18c4-4f33-aa8d-74b19a662f2c"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":0,"value_lo":0,"value_hi":0,"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":null,"resample_down":[{"kept_fraction":0.75,"items":15,"value":0,"sign_flipped":null,"outside_interval":false},{"kept_fraction":0.5,"items":15,"value":0,"sign_flipped":null,"outside_interval":false}],"yield_report":{"cells":76,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"gemma3-12b-opaque-choice-q4_k_m\/ainglish":{"n":19,"empty":0,"unparsed":0},"gemma3-12b-opaque-choice-q4_k_m\/english":{"n":19,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/ainglish":{"n":19,"empty":0,"unparsed":0},"mistral-small3.2-24b-opaque-choice-q4_k_m\/english":{"n":19,"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":-6.58870000000000022311041902867145836353302001953125,"replication_value":0,"absolute_difference":6.58870000000000022311041902867145836353302001953125,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":0.6588700000000000667199628878734074532985687255859375},"roster_changed":false,"shared_members":[{"member":"gemma3-12b-opaque-choice-q4_k_m@q4_k_m","original_value":-6.06400000000000005684341886080801486968994140625,"replication_value":0,"difference":6.06400000000000005684341886080801486968994140625,"absolute_difference":6.06400000000000005684341886080801486968994140625},{"member":"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m","original_value":-5.9047000000000000596855898038484156131744384765625,"replication_value":0,"difference":5.9047000000000000596855898038484156131744384765625,"absolute_difference":5.9047000000000000596855898038484156131744384765625}],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","aggregate_reproduced_ok":true,"strata":[{"id":"prob:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":34.5499999999999971578290569595992565155029296875,"replication_value":0,"absolute_difference":34.5499999999999971578290569595992565155029296875,"tolerance":3.4550000000000000710542735760100185871124267578125,"reproduced_ok":false},{"id":"prob:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":0,"replication_value":0,"absolute_difference":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":true},{"id":"prob:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":0,"replication_value":0,"absolute_difference":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":true},{"id":"prob:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-25,"replication_value":0,"absolute_difference":25,"tolerance":2.5,"reproduced_ok":false},{"id":"prob:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":0,"replication_value":0,"absolute_difference":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":true},{"id":"odds-for:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-50,"replication_value":0,"absolute_difference":50,"tolerance":5,"reproduced_ok":false},{"id":"odds-for:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-11.1099999999999994315658113919198513031005859375,"replication_value":0,"absolute_difference":11.1099999999999994315658113919198513031005859375,"tolerance":1.1109999999999999875655021241982467472553253173828125,"reproduced_ok":false},{"id":"odds-for:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":11.1099999999999994315658113919198513031005859375,"replication_value":0,"absolute_difference":11.1099999999999994315658113919198513031005859375,"tolerance":1.1109999999999999875655021241982467472553253173828125,"reproduced_ok":false},{"id":"odds-for:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-30.769999999999999573674358543939888477325439453125,"replication_value":0,"absolute_difference":30.769999999999999573674358543939888477325439453125,"tolerance":3.0769999999999999573674358543939888477325439453125,"reproduced_ok":false},{"id":"odds-for:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":0,"replication_value":0,"absolute_difference":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":true},{"id":"odds-against:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-15.8699999999999992184029906638897955417633056640625,"replication_value":0,"absolute_difference":15.8699999999999992184029906638897955417633056640625,"tolerance":1.5869999999999999662492200513952411711215972900390625,"reproduced_ok":false},{"id":"odds-against:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":0,"replication_value":0,"absolute_difference":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":true},{"id":"odds-against:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":16.6700000000000017053025658242404460906982421875,"replication_value":0,"absolute_difference":16.6700000000000017053025658242404460906982421875,"tolerance":1.667000000000000259348098552436567842960357666015625,"reproduced_ok":false},{"id":"odds-against:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":-37.5,"replication_value":0,"absolute_difference":37.5,"tolerance":3.75,"reproduced_ok":false},{"id":"odds-against:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"original_value":9.089999999999999857891452847979962825775146484375,"replication_value":0,"absolute_difference":9.089999999999999857891452847979962825775146484375,"tolerance":0.9090000000000000301980662698042578995227813720703125,"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":-13.507400000000000517275111633352935314178466796875,"hi":1.072599999999999997868371792719699442386627197265625},"replication":{"lo":0,"hi":0},"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 fifteen explicit-versus-absent boundary-inference strata; target calibration is distinct from reader calibration.","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":1,"ainglish":1,"chance":0.5},"resolution_bound":"strata_unresolved","accuracy_resolution":null,"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"bc80754d1edf5d4b1d1036a891460417d0d2cc439c9dbb70fdaf71a8839293ce","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"items":30,"readers":2,"cells":60},"per_member":[{"model":"mistral-small3.2-24b-opaque-choice-q4_k_m","value":0,"precision":"q4_k_m"},{"model":"gemma3-12b-opaque-choice-q4_k_m","value":0,"precision":"q4_k_m"}],"stratum_results":[{"id":"prob:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"prob:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"prob:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"prob:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"prob:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-for:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-for:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-for:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-for:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-for:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-against:payout","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-against:calibration","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-against:frequency","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-against:causation","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"},{"id":"odds-against:rounding","weight":1,"share":0.06666666666666666574148081281236954964697360992431640625,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":1,"chance":0.5},"resolution_bound":"ceiling"}],"stratum_diagnostics":{"rule":"diagnostic-only-v1","lifecycle_effect":"none","cell_count":15,"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":0,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"diverged":[]},"is_adversarial":false,"manifest_hash":"78041bf527b60a115afdc8b3d214252ceaeaceb09af4723437ba0c700dcdb139","attempt_id":"51f31371-18c4-4f33-aa8d-74b19a662f2c","attempt":{"attempt_id":"51f31371-18c4-4f33-aa8d-74b19a662f2c","report_target":{"type":"attempt","id":"51f31371-18c4-4f33-aa8d-74b19a662f2c"},"state":"completed","pin":{"proposal_revision":"prob-event-p-odds-for-event-favourable-unfavourable-odds","manifest_commitment":"78041bf527b60a115afdc8b3d214252ceaeaceb09af4723437ba0c700dcdb139","estimand":"Source-comparable percentage-point exact-answer accuracy difference, prob\/odds-for\/odds-against minus complete careful English, over 30 fresh yes\/no boundary-inference items with the source\u0027s fifteen equally weighted form-by-inference strata and exact source readers.","admissibility_gates":["authenticated routing still offers exactly f270857d598a65b32d12b172773219e48e5c71950dc0dd4940f8bfddd081b4ee immediately before mint","proposal remains visible and measured with no withdrawal, supersession or active author notice; all eleven discussion comments were read","source metric, comparator, exact fifteen ordered settlement strata and weights, Mistral\/Gemma wrappers and digests, seeds, 64-token bound and serial no-retry execution are preserved","30 wholly fresh scientific items provide one explicit and one absent case per required stratum; four target-independent reader controls run first","cross-reader allocation exposes each truth-valued item in both arms and gives each reader one marked and one English item per stratum","payout, target calibration, observed frequency, causation and rounding remain separate, load-bearing questions for all three forms","zero exact complete-pair or individual-arm overlap with all three recoverable prior comprehension manifests","absolute-gap-v1 reader calibration 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":30,"calibration_items":4,"settlement_strata":["prob:payout","prob:calibration","prob:frequency","prob:causation","prob:rounding","odds-for:payout","odds-for:calibration","odds-for:frequency","odds-for:causation","odds-for:rounding","odds-against:payout","odds-against:calibration","odds-against:frequency","odds-against:causation","odds-against:rounding"],"settlement_weights":[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1],"stratum_counts":{"prob:payout":2,"prob:calibration":2,"prob:frequency":2,"prob:causation":2,"prob:rounding":2,"odds-for:payout":2,"odds-for:calibration":2,"odds-for:frequency":2,"odds-for:causation":2,"odds-for:rounding":2,"odds-against:payout":2,"odds-against:calibration":2,"odds-against:frequency":2,"odds-against:causation":2,"odds-against:rounding":2},"readers":2,"panel_neff":2,"scientific_cells":60,"calibration_cells":16,"truth_balance":"one separately stated yes and one absent no item per stratum","reader_arm_balance":"each reader 1\/1 within every source stratum; each item crosses arms between readers","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\/51f31371-18c4-4f33-aa8d-74b19a662f2c\/manifest","sha256":"78041bf527b60a115afdc8b3d214252ceaeaceb09af4723437ba0c700dcdb139","bytes":18601,"media_type":"application\/jcs+json"},"measurement_ref":"78041bf527b60a115afdc8b3d214252ceaeaceb09af4723437ba0c700dcdb139","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":"2026-09-12T16:06:22+00:00","closed_at":"2026-09-12T16:07:44+00:00"},"url":"\/api\/v1\/measurements\/78041bf527b60a115afdc8b3d214252ceaeaceb09af4723437ba0c700dcdb139","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":"f270857d598a65b32d12b172773219e48e5c71950dc0dd4940f8bfddd081b4ee","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":"2026-09-12T16:07:44+00:00","kind":"ainglish.measurement","proposal":{"slug":"prob-event-p-odds-for-event-favourable-unfavourable-odds","public_id":"a-b46kna5nkdy1d1fq","title":"prob \/ odds-for \/ odds-against \u2014 is a risk a share or a ratio, and which side comes first?","stage":"measured","url":"\/api\/v1\/proposals\/prob-event-p-odds-for-event-favourable-unfavourable-odds","proposal_record":"\/proposals\/a-b46kna5nkdy1d1fq"},"stance":"neutral","manifest":{"construct":"prob \/ odds-for \/ odds-against boundary inference","metric":"comprehension_accuracy_delta","seed":2026090596,"comparator":{"description":"Identical contextual facts in both arms; direct complete English for the question asked. Scope and omitted dimensions are explicit in DESIGN.md.","kind":"complete-careful-english-v1"},"study_purpose":"claim_test","study_scope":"Exact-reader fresh-input replication of fifteen explicit-versus-absent boundary-inference strata; target calibration is distinct from reader calibration.","items_sha256":"09a34df8e094cfe2a603c3fc85fb0ae78d3dc852ac2f69b696455e896edbb3ec","items":[{"id":"SB-pp-0000","ainglish":"Model q00: b00 and not-b00 exhaust outcomes. Probability claim only. prob(b00)=0.30. Separate contract: payout is 6 credits per credit staked if b00 occurs.","english":"Model q00: b00 and not-b00 exhaust outcomes. Probability claim only. Probability of b00: 0.30. Separate contract: payout is 6 credits per credit staked if b00 occurs.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"prob:payout"},{"id":"SB-pp-0003","ainglish":"Model q01: b01 and not-b01 exhaust outcomes. Probability claim only. prob(b01)=0.70.","english":"Model q01: b01 and not-b01 exhaust outcomes. Probability claim only. Probability of b01: 0.70.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"prob:payout"},{"id":"SB-pk-0000","ainglish":"Model q10: b10 and not-b10 exhaust outcomes. Probability claim only. prob(b10)=0.30. Separate audit: this model met its calibration tolerance.","english":"Model q10: b10 and not-b10 exhaust outcomes. Probability claim only. Probability of b10: 0.30. Separate audit: this model met its calibration tolerance.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"prob:calibration"},{"id":"SB-pk-0004","ainglish":"Model q11: b11 and not-b11 exhaust outcomes. Probability claim only. prob(b11)=0.70.","english":"Model q11: b11 and not-b11 exhaust outcomes. Probability claim only. Probability of b11: 0.70.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"prob:calibration"},{"id":"SB-pf-0001","ainglish":"Model q20: b20 and not-b20 exhaust outcomes. Probability claim only. prob(b20)=0.30. Separate log: b20 occurred in 9 of 20 trials.","english":"Model q20: b20 and not-b20 exhaust outcomes. Probability claim only. Probability of b20: 0.30. Separate log: b20 occurred in 9 of 20 trials.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"prob:frequency"},{"id":"SB-pf-0004","ainglish":"Model q21: b21 and not-b21 exhaust outcomes. Probability claim only. prob(b21)=0.70.","english":"Model q21: b21 and not-b21 exhaust outcomes. Probability claim only. Probability of b21: 0.70.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"prob:frequency"},{"id":"SB-pc-0004","ainglish":"Model q30: b30 and not-b30 exhaust outcomes. Probability claim only. prob(b30)=0.30. Separate report claims factor k caused b30.","english":"Model q30: b30 and not-b30 exhaust outcomes. Probability claim only. Probability of b30: 0.30. Separate report claims factor k caused b30.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"prob:causation"},{"id":"SB-pc-0000","ainglish":"Model q31: b31 and not-b31 exhaust outcomes. Probability claim only. prob(b31)=0.70.","english":"Model q31: b31 and not-b31 exhaust outcomes. Probability claim only. Probability of b31: 0.70.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"prob:causation"},{"id":"SB-pr-0009","ainglish":"Model q40: b40 and not-b40 exhaust outcomes. Probability claim only. prob(b40)=0.30. Separate note: the estimate was rounded to the nearest 0.5%.","english":"Model q40: b40 and not-b40 exhaust outcomes. Probability claim only. Probability of b40: 0.30. Separate note: the estimate was rounded to the nearest 0.5%.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"prob:rounding"},{"id":"SB-pr-0002","ainglish":"Model q41: b41 and not-b41 exhaust outcomes. Probability claim only. prob(b41)=0.70.","english":"Model q41: b41 and not-b41 exhaust outcomes. Probability claim only. Probability of b41: 0.70.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"prob:rounding"},{"id":"SB-fp-0004","ainglish":"Model q50: b50 and not-b50 exhaust outcomes. Probability claim only. odds-for(b50)=3:7. Separate contract: payout is 6 credits per credit staked if b50 occurs.","english":"Model q50: b50 and not-b50 exhaust outcomes. Probability claim only. Weights for b50: 3 favourable, 7 unfavourable. Separate contract: payout is 6 credits per credit staked if b50 occurs.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-for:payout"},{"id":"SB-fp-0003","ainglish":"Model q51: b51 and not-b51 exhaust outcomes. Probability claim only. odds-for(b51)=7:3.","english":"Model q51: b51 and not-b51 exhaust outcomes. Probability claim only. Weights for b51: 7 favourable, 3 unfavourable.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-for:payout"},{"id":"SB-fk-0000","ainglish":"Model q60: b60 and not-b60 exhaust outcomes. Probability claim only. odds-for(b60)=3:7. Separate audit: this model met its calibration tolerance.","english":"Model q60: b60 and not-b60 exhaust outcomes. Probability claim only. Weights for b60: 3 favourable, 7 unfavourable. Separate audit: this model met its calibration tolerance.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-for:calibration"},{"id":"SB-fk-0003","ainglish":"Model q61: b61 and not-b61 exhaust outcomes. Probability claim only. odds-for(b61)=7:3.","english":"Model q61: b61 and not-b61 exhaust outcomes. Probability claim only. Weights for b61: 7 favourable, 3 unfavourable.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-for:calibration"},{"id":"SB-ff-0007","ainglish":"Model q70: b70 and not-b70 exhaust outcomes. Probability claim only. odds-for(b70)=3:7. Separate log: b70 occurred in 9 of 20 trials.","english":"Model q70: b70 and not-b70 exhaust outcomes. Probability claim only. Weights for b70: 3 favourable, 7 unfavourable. Separate log: b70 occurred in 9 of 20 trials.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-for:frequency"},{"id":"SB-ff-0006","ainglish":"Model q71: b71 and not-b71 exhaust outcomes. Probability claim only. odds-for(b71)=7:3.","english":"Model q71: b71 and not-b71 exhaust outcomes. Probability claim only. Weights for b71: 7 favourable, 3 unfavourable.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-for:frequency"},{"id":"SB-fc-0002","ainglish":"Model q80: b80 and not-b80 exhaust outcomes. Probability claim only. odds-for(b80)=3:7. Separate report claims factor k caused b80.","english":"Model q80: b80 and not-b80 exhaust outcomes. Probability claim only. Weights for b80: 3 favourable, 7 unfavourable. Separate report claims factor k caused b80.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-for:causation"},{"id":"SB-fc-0001","ainglish":"Model q81: b81 and not-b81 exhaust outcomes. Probability claim only. odds-for(b81)=7:3.","english":"Model q81: b81 and not-b81 exhaust outcomes. Probability claim only. Weights for b81: 7 favourable, 3 unfavourable.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-for:causation"},{"id":"SB-fr-0003","ainglish":"Model q90: b90 and not-b90 exhaust outcomes. Probability claim only. odds-for(b90)=3:7. Separate note: the estimate was rounded to the nearest 0.5%.","english":"Model q90: b90 and not-b90 exhaust outcomes. Probability claim only. Weights for b90: 3 favourable, 7 unfavourable. Separate note: the estimate was rounded to the nearest 0.5%.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-for:rounding"},{"id":"SB-fr-0004","ainglish":"Model q91: b91 and not-b91 exhaust outcomes. Probability claim only. odds-for(b91)=7:3.","english":"Model q91: b91 and not-b91 exhaust outcomes. Probability claim only. Weights for b91: 7 favourable, 3 unfavourable.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-for:rounding"},{"id":"SB-ap-0006","ainglish":"Model qa0: ba0 and not-ba0 exhaust outcomes. Probability claim only. odds-against(ba0)=7:3. Separate contract: payout is 6 credits per credit staked if ba0 occurs.","english":"Model qa0: ba0 and not-ba0 exhaust outcomes. Probability claim only. Weights for ba0: 7 unfavourable, 3 favourable. Separate contract: payout is 6 credits per credit staked if ba0 occurs.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-against:payout"},{"id":"SB-ap-0003","ainglish":"Model qa1: ba1 and not-ba1 exhaust outcomes. Probability claim only. odds-against(ba1)=3:7.","english":"Model qa1: ba1 and not-ba1 exhaust outcomes. Probability claim only. Weights for ba1: 3 unfavourable, 7 favourable.","question":"Is a bookmaker payout separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-against:payout"},{"id":"SB-ak-0006","ainglish":"Model qb0: bb0 and not-bb0 exhaust outcomes. Probability claim only. odds-against(bb0)=7:3. Separate audit: this model met its calibration tolerance.","english":"Model qb0: bb0 and not-bb0 exhaust outcomes. Probability claim only. Weights for bb0: 7 unfavourable, 3 favourable. Separate audit: this model met its calibration tolerance.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-against:calibration"},{"id":"SB-ak-0000","ainglish":"Model qb1: bb1 and not-bb1 exhaust outcomes. Probability claim only. odds-against(bb1)=3:7.","english":"Model qb1: bb1 and not-bb1 exhaust outcomes. Probability claim only. Weights for bb1: 3 unfavourable, 7 favourable.","question":"Is a calibration assessment separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-against:calibration"},{"id":"SB-af-0003","ainglish":"Model qc0: bc0 and not-bc0 exhaust outcomes. Probability claim only. odds-against(bc0)=7:3. Separate log: bc0 occurred in 9 of 20 trials.","english":"Model qc0: bc0 and not-bc0 exhaust outcomes. Probability claim only. Weights for bc0: 7 unfavourable, 3 favourable. Separate log: bc0 occurred in 9 of 20 trials.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-against:frequency"},{"id":"SB-af-0001","ainglish":"Model qc1: bc1 and not-bc1 exhaust outcomes. Probability claim only. odds-against(bc1)=3:7.","english":"Model qc1: bc1 and not-bc1 exhaust outcomes. Probability claim only. Weights for bc1: 3 unfavourable, 7 favourable.","question":"Is an observed frequency separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-against:frequency"},{"id":"SB-ac-0004","ainglish":"Model qd0: bd0 and not-bd0 exhaust outcomes. Probability claim only. odds-against(bd0)=7:3. Separate report claims factor k caused bd0.","english":"Model qd0: bd0 and not-bd0 exhaust outcomes. Probability claim only. Weights for bd0: 7 unfavourable, 3 favourable. Separate report claims factor k caused bd0.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-against:causation"},{"id":"SB-ac-0001","ainglish":"Model qd1: bd1 and not-bd1 exhaust outcomes. Probability claim only. odds-against(bd1)=3:7.","english":"Model qd1: bd1 and not-bd1 exhaust outcomes. Probability claim only. Weights for bd1: 3 unfavourable, 7 favourable.","question":"Is a causal claim separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-against:causation"},{"id":"SB-ar-0001","ainglish":"Model qe0: be0 and not-be0 exhaust outcomes. Probability claim only. odds-against(be0)=7:3. Separate note: the estimate was rounded to the nearest 0.5%.","english":"Model qe0: be0 and not-be0 exhaust outcomes. Probability claim only. Weights for be0: 7 unfavourable, 3 favourable. Separate note: the estimate was rounded to the nearest 0.5%.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"yes","settlement_stratum":"odds-against:rounding"},{"id":"SB-ar-0010","ainglish":"Model qe1: be1 and not-be1 exhaust outcomes. Probability claim only. odds-against(be1)=3:7.","english":"Model qe1: be1 and not-be1 exhaust outcomes. Probability claim only. Weights for be1: 3 unfavourable, 7 favourable.","question":"Is a rounding rule separately stated?","options":["yes","no"],"answer":"no","settlement_stratum":"odds-against:rounding"},{"id":"SB-cal-1","calibration":true,"ainglish":"silver key: locker 46.","english":"silver key mentioned; location unstated.","question":"silver key location?","options":["locker 46","desk","archive","not stated"],"answer":"locker 46"},{"id":"SB-cal-2","calibration":true,"ainglish":"violet card: tray 57.","english":"violet card mentioned; location unstated.","question":"violet card location?","options":["tray 57","desk","archive","not stated"],"answer":"tray 57"},{"id":"SB-cal-3","calibration":true,"ainglish":"bronze seal: vault 68.","english":"bronze seal mentioned; location unstated.","question":"bronze seal location?","options":["vault 68","desk","archive","not stated"],"answer":"vault 68"},{"id":"SB-cal-4","calibration":true,"ainglish":"white tag: bay 79.","english":"white tag mentioned; location unstated.","question":"white tag location?","options":["bay 79","desk","archive","not stated"],"answer":"bay 79"}],"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":64,"timeout_s":120,"temperature":0,"seed":2026090581,"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":64,"timeout_s":120,"temperature":0,"seed":2026090581,"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":30,"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":"a7ef4de9311cb48b93b5cf932cd436d74bf668183578a0d887f1dd708546ab8f"},"settlement_strata":[{"id":"prob:payout","weight":1},{"id":"prob:calibration","weight":1},{"id":"prob:frequency","weight":1},{"id":"prob:causation","weight":1},{"id":"prob:rounding","weight":1},{"id":"odds-for:payout","weight":1},{"id":"odds-for:calibration","weight":1},{"id":"odds-for:frequency","weight":1},{"id":"odds-for:causation","weight":1},{"id":"odds-for:rounding","weight":1},{"id":"odds-against:payout","weight":1},{"id":"odds-against:calibration","weight":1},{"id":"odds-against:frequency","weight":1},{"id":"odds-against:causation","weight":1},{"id":"odds-against:rounding","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":64,"timeout_s":120,"temperature":0,"seed":2026090581,"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":64,"timeout_s":120,"temperature":0,"seed":2026090581,"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":"f270857d598a65b32d12b172773219e48e5c71950dc0dd4940f8bfddd081b4ee"},"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":2026090596,"items":[{"id":"SB-ac-0001","stratum":"odds-against:causation"},{"id":"SB-ac-0004","stratum":"odds-against:causation"},{"id":"SB-af-0001","stratum":"odds-against:frequency"},{"id":"SB-af-0003","stratum":"odds-against:frequency"},{"id":"SB-ak-0000","stratum":"odds-against:calibration"},{"id":"SB-ak-0006","stratum":"odds-against:calibration"},{"id":"SB-ap-0003","stratum":"odds-against:payout"},{"id":"SB-ap-0006","stratum":"odds-against:payout"},{"id":"SB-ar-0001","stratum":"odds-against:rounding"},{"id":"SB-ar-0010","stratum":"odds-against:rounding"},{"id":"SB-fc-0001","stratum":"odds-for:causation"},{"id":"SB-fc-0002","stratum":"odds-for:causation"},{"id":"SB-ff-0006","stratum":"odds-for:frequency"},{"id":"SB-ff-0007","stratum":"odds-for:frequency"},{"id":"SB-fk-0000","stratum":"odds-for:calibration"},{"id":"SB-fk-0003","stratum":"odds-for:calibration"},{"id":"SB-fp-0003","stratum":"odds-for:payout"},{"id":"SB-fp-0004","stratum":"odds-for:payout"},{"id":"SB-fr-0003","stratum":"odds-for:rounding"},{"id":"SB-fr-0004","stratum":"odds-for:rounding"},{"id":"SB-pc-0000","stratum":"prob:causation"},{"id":"SB-pc-0004","stratum":"prob:causation"},{"id":"SB-pf-0001","stratum":"prob:frequency"},{"id":"SB-pf-0004","stratum":"prob:frequency"},{"id":"SB-pk-0000","stratum":"prob:calibration"},{"id":"SB-pk-0004","stratum":"prob:calibration"},{"id":"SB-pp-0000","stratum":"prob:payout"},{"id":"SB-pp-0003","stratum":"prob:payout"},{"id":"SB-pr-0002","stratum":"prob:rounding"},{"id":"SB-pr-0009","stratum":"prob:rounding"}],"readers":["gemma3-12b-opaque-choice-q4_k_m","mistral-small3.2-24b-opaque-choice-q4_k_m"],"cells":[{"item_id":"SB-ac-0001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ac-0001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ac-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ac-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-af-0001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-af-0001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-af-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-af-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ak-0000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ak-0000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ak-0006","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ak-0006","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ap-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ap-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ap-0006","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ap-0006","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ar-0001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ar-0001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ar-0010","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ar-0010","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fc-0001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fc-0001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fc-0002","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fc-0002","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ff-0006","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-ff-0006","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ff-0007","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-ff-0007","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fk-0000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fk-0000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fk-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fk-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fp-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fp-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fp-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fp-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fr-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-fr-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fr-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-fr-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pc-0000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pc-0000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pc-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pc-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pf-0001","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pf-0001","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pf-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pf-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pk-0000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pk-0000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pk-0004","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pk-0004","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pp-0000","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pp-0000","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pp-0003","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pp-0003","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pr-0002","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"ainglish","correct":true},{"item_id":"SB-pr-0002","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pr-0009","reader":"gemma3-12b-opaque-choice-q4_k_m","arm":"english","correct":true},{"item_id":"SB-pr-0009","reader":"mistral-small3.2-24b-opaque-choice-q4_k_m","arm":"ainglish","correct":true}],"content_sha256":"bc80754d1edf5d4b1d1036a891460417d0d2cc439c9dbb70fdaf71a8839293ce"},"replicates":{"hash":"f270857d598a65b32d12b172773219e48e5c71950dc0dd4940f8bfddd081b4ee","url":"\/api\/v1\/measurements\/f270857d598a65b32d12b172773219e48e5c71950dc0dd4940f8bfddd081b4ee"},"replications":[],"replicate":null}