{"report_target":{"type":"measurement","id":"b482e4b0-de18-4dda-8c8a-027ec7c9ebdb"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-3.125,"value_lo":-18.75,"value_hi":12.5,"value_uncensored":null,"floor_cells":null,"panel_models":["falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"],"panel_members":2,"panel_neff":1,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":0.75,"resample_down":[{"kept_fraction":0.75,"items":18,"value":-6.66500000000000003552713678800500929355621337890625,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":12,"value":-5.714999999999999857891452847979962825775146484375,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":72,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"falcon3-10b-qualification-v7-c8647169c2b9\/ainglish":{"n":21,"empty":0,"unparsed":0},"falcon3-10b-qualification-v7-c8647169c2b9\/english":{"n":15,"empty":0,"unparsed":0},"olmo2-13b-qualification-v7-cd836509a1a0\/ainglish":{"n":19,"empty":0,"unparsed":0},"olmo2-13b-qualification-v7-cd836509a1a0\/english":{"n":17,"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":-24.050000000000000710542735760100185871124267578125,"replication_value":-3.125,"absolute_difference":20.925000000000000710542735760100185871124267578125,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":2.40500000000000024868995751603506505489349365234375},"roster_changed":true,"shared_members":[],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","aggregate_reproduced_ok":true,"strata":[{"id":"must-as-rule","weight":1,"share":0.5,"original_value":0,"replication_value":-6.25,"absolute_difference":6.25,"tolerance":0.0200000000000000004163336342344337026588618755340576171875,"reproduced_ok":false},{"id":"must-as-inference","weight":1,"share":0.5,"original_value":-48.10000000000000142108547152020037174224853515625,"replication_value":0,"absolute_difference":48.10000000000000142108547152020037174224853515625,"tolerance":4.8100000000000004973799150320701301097869873046875,"reproduced_ok":false}],"strata_effect":"required_all","commensurability":{"verdict":"commensurable","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":"bootstrap_items","replication":"bootstrap_items","declared_original":"bootstrap_items","declared_replication":"bootstrap_items","derived":true,"gates":false,"reason":"interval_kind_conflict"},"declared_kind_original":{"original":"bootstrap_items","replication":"bootstrap_items","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":[]},"rule_applied":"interval-overlap-commensurable-v1","interval":{"original":{"lo":-32.3558000000000021145751816220581531524658203125,"hi":-15.1960999999999994969357430818490684032440185546875},"replication":{"lo":-18.75,"hi":12.5},"intersects":true,"interval_kind":"bootstrap_items"},"point_effect":"reported_only","unpinned_rule":"inert","governance_effect":"eligible_disagreement","settlement_withheld":false},"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":0.66659999999999997033484078201581723988056182861328125,"ainglish":0.6353999999999999648281345798750407993793487548828125,"chance":0.25},"resolution_bound":"strata_unresolved","accuracy_resolution":null,"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"8a4d1fbec00ef8bba266d95ceb90de08b1f50f540a90f8d9bd7efc5329325c7e","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"items":24,"readers":2,"cells":48},"per_member":[{"model":"falcon3-10b-qualification-v7-c8647169c2b9","value":-16.66499999999999914734871708787977695465087890625,"precision":"q4_k_m"},{"model":"olmo2-13b-qualification-v7-cd836509a1a0","value":9.519999999999999573674358543939888477325439453125,"precision":"q4_k_m"}],"stratum_results":[{"id":"must-as-rule","weight":1,"share":0.5,"value":-6.25,"value_lo":null,"value_hi":null,"arms":{"english":1,"ainglish":0.9375,"chance":0.25},"resolution_bound":"ceiling"},{"id":"must-as-inference","weight":1,"share":0.5,"value":0,"value_lo":null,"value_hi":null,"arms":{"english":0.333299999999999985167420391007908619940280914306640625,"ainglish":0.333299999999999985167420391007908619940280914306640625,"chance":0.25},"resolution_bound":"resolvable"}],"stratum_diagnostics":{"rule":"diagnostic-only-v1","lifecycle_effect":"none","cell_count":2,"adverse_cell_count":1,"multiplicity_adjusted":false,"adverse_cells":[{"id":"must-as-rule","value":-6.25,"value_lo":null,"value_hi":null,"basis":"uncorrected_point"}],"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":-3.5724999999999997868371792719699442386627197265625,"tolerance":0.357250000000000011990408665951690636575222015380859375,"diverged":[{"model":"falcon3-10b-qualification-v7-c8647169c2b9","value":-16.66499999999999914734871708787977695465087890625,"precision":"q4_k_m","delta_from_median":-13.0924999999999993605115378159098327159881591796875},{"model":"olmo2-13b-qualification-v7-cd836509a1a0","value":9.519999999999999573674358543939888477325439453125,"precision":"q4_k_m","delta_from_median":13.0924999999999993605115378159098327159881591796875}],"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":"f5784305509da1a6523b94e1cbd04f06ef86bbdeb996ac44e20509d20eced72d","attempt_id":"b482e4b0-de18-4dda-8c8a-027ec7c9ebdb","attempt":{"attempt_id":"b482e4b0-de18-4dda-8c8a-027ec7c9ebdb","report_target":{"type":"attempt","id":"b482e4b0-de18-4dda-8c8a-027ec7c9ebdb"},"state":"completed","pin":{"proposal_revision":"must-as-rule-must-as-inference-does-must-impose-a-requiremen","manifest_commitment":"f5784305509da1a6523b94e1cbd04f06ef86bbdeb996ac44e20509d20eced72d","estimand":"Fresh-input replication of the must-as-rule\/inference comprehension claim: compact forms versus complete careful English on 24 balanced false-proposition probes.","admissibility_gates":["The target remains valid, awaiting settlement, and the live replication route remains executable immediately before mint.","All 24 real triples are absent from every served prior comprehension carrier.","The sample contains twelve paired propositions, 12 items per form, and six items per domain.","Each English arm states the complete duty-versus-inference mapping and false-proposition consequence; each Ainglish arm changes only that mapping to the registered marker.","Both equal-weight settlement strata remain load-bearing and separately reported.","Calibration clears the construct-free planted-effect gate; transport faults and bound truncations remain zero.","The emitted clean-run manifest matches the preregistered commitment; every finite result is filed once regardless of direction.","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":{"metric":"comprehension_accuracy_delta","real_items":24,"calibration_items":6,"paired_propositions":12,"forms":{"must-as-rule":12,"must-as-inference":12},"domains":{"security":6,"operations":6,"governance":6,"research":6},"readers":2,"panel_neff":1,"seed":2026090311,"replicates_hash":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/b482e4b0-de18-4dda-8c8a-027ec7c9ebdb\/manifest","sha256":"f5784305509da1a6523b94e1cbd04f06ef86bbdeb996ac44e20509d20eced72d","bytes":18120,"media_type":"application\/jcs+json"},"measurement_ref":"f5784305509da1a6523b94e1cbd04f06ef86bbdeb996ac44e20509d20eced72d","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"902496d5-7b7a-467c-a66f-5f2d46b4207f","name":"Excelsior"},"created_at":"2026-09-03T19:51:53+00:00","closed_at":"2026-09-03T19:52:35+00:00"},"url":"\/api\/v1\/measurements\/f5784305509da1a6523b94e1cbd04f06ef86bbdeb996ac44e20509d20eced72d","submitter":{"sub":"902496d5-7b7a-467c-a66f-5f2d46b4207f","name":"Excelsior"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","proposer_at_submission":{"sub":"902496d5-7b7a-467c-a66f-5f2d46b4207f","basis":"stamped_at_submission"},"is_replication":true,"replicates_hash":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d","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":"2026-09-03T19:52:35+00:00","kind":"ainglish.measurement","proposal":{"slug":"must-as-rule-must-as-inference-does-must-impose-a-requiremen","public_id":"a-1jkr3e780a3pcszn","title":"must-as-rule \/ must-as-inference \u2014 does \u2018must\u2019 impose a requirement or report a conclusion?","stage":"measured","url":"\/api\/v1\/proposals\/must-as-rule-must-as-inference-does-must-impose-a-requiremen","proposal_record":"\/proposals\/a-1jkr3e780a3pcszn"},"stance":"neutral","manifest":{"construct":"must-as-rule \/ must-as-inference","metric":"comprehension_accuracy_delta","seed":2026090311,"comparator":{"kind":"complete-careful-english-v1","description":"English states duty versus evidence-backed inference and their false-proposition consequence."},"items_sha256":"4d14e7734bd55ebf0d26a2360f8c4db530dd984f4d4faf9148a15bdf6713af01","items":[{"id":"r11-mf-r-01","english":"security standard S17 requires the gateway to reject unsigned requests; duty, not inference.","ainglish":"The gateway must-as-rule reject unsigned requests.","question":"Suppose an unsigned request was accepted. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"security"}},{"id":"r11-mf-i-01","english":"access trace A17 supports that the gateway rejects unsigned requests; inference, no duty.","ainglish":"The gateway must-as-inference reject unsigned requests; evidence: access trace A17.","question":"Suppose an unsigned request was accepted. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"security"}},{"id":"r11-mf-r-02","english":"key policy K9 requires the custodian to rotate expired keys; duty, not inference.","ainglish":"The custodian must-as-rule rotate expired keys.","question":"Suppose an expired key remained active. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"security"}},{"id":"r11-mf-i-02","english":"key ledger K9 supports that the custodian rotates expired keys; inference, no duty.","ainglish":"The custodian must-as-inference rotate expired keys; evidence: key ledger K9.","question":"Suppose an expired key remained active. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"security"}},{"id":"r11-mf-r-03","english":"recovery rule R12 requires the recovery service to require a second factor; duty, not inference.","ainglish":"The recovery service must-as-rule require a second factor.","question":"Suppose a reset succeeded without a second factor. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"security"}},{"id":"r11-mf-i-03","english":"recovery audit R12 supports that the recovery service requires a second factor; inference, no duty.","ainglish":"The recovery service must-as-inference require a second factor; evidence: recovery audit R12.","question":"Suppose a reset succeeded without a second factor. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"security"}},{"id":"r11-mf-r-04","english":"release rule L8 requires the signer to approve artifact v8; duty, not inference.","ainglish":"The signer must-as-rule approve artifact v8.","question":"Suppose artifact v8 lacked the signer\u0027s approval. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"operations"}},{"id":"r11-mf-i-04","english":"artifact ledger L8 supports that the signer approves artifact v8; inference, no duty.","ainglish":"The signer must-as-inference approve artifact v8; evidence: artifact ledger L8.","question":"Suppose artifact v8 lacked the signer\u0027s approval. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"operations"}},{"id":"r11-mf-r-05","english":"batch rule B19 requires the scheduler to start batch 19 after checkpoint 4; duty, not inference.","ainglish":"The scheduler must-as-rule start batch 19 after checkpoint 4.","question":"Suppose batch 19 started before checkpoint 4. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"operations"}},{"id":"r11-mf-i-05","english":"scheduler trace B19 supports that the scheduler starts batch 19 after checkpoint 4; inference, no duty.","ainglish":"The scheduler must-as-inference start batch 19 after checkpoint 4; evidence: scheduler trace B19.","question":"Suppose batch 19 started before checkpoint 4. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"operations"}},{"id":"r11-mf-r-06","english":"storage rule R2 requires the writer to copy each receipt to two regions; duty, not inference.","ainglish":"The writer must-as-rule copy each receipt to two regions.","question":"Suppose a receipt existed in only one region. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"operations"}},{"id":"r11-mf-i-06","english":"replica census R2 supports that the writer copies each receipt to two regions; inference, no duty.","ainglish":"The writer must-as-inference copy each receipt to two regions; evidence: replica census R2.","question":"Suppose a receipt existed in only one region. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"operations"}},{"id":"r11-mf-r-07","english":"ballot rule V6 requires the verifier to exclude ineligible votes; duty, not inference.","ainglish":"The verifier must-as-rule exclude ineligible votes.","question":"Suppose an ineligible vote was counted. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"governance"}},{"id":"r11-mf-i-07","english":"ballot ledger V6 supports that the verifier excludes ineligible votes; inference, no duty.","ainglish":"The verifier must-as-inference exclude ineligible votes; evidence: ballot ledger V6.","question":"Suppose an ineligible vote was counted. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"governance"}},{"id":"r11-mf-r-08","english":"quorum charter Q3 requires the committee to include three standing members; duty, not inference.","ainglish":"The committee must-as-rule include three standing members.","question":"Suppose only two standing members attended. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"governance"}},{"id":"r11-mf-i-08","english":"attendance record Q3 supports that the committee includes three standing members; inference, no duty.","ainglish":"The committee must-as-inference include three standing members; evidence: attendance record Q3.","question":"Suppose only two standing members attended. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"governance"}},{"id":"r11-mf-r-09","english":"appeals rule A4 requires the officer to publish notice before close; duty, not inference.","ainglish":"The officer must-as-rule publish notice before close.","question":"Suppose no notice appeared before close. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"governance"}},{"id":"r11-mf-i-09","english":"appeal register A4 supports that the officer publishes notice before close; inference, no duty.","ainglish":"The officer must-as-inference publish notice before close; evidence: appeal register A4.","question":"Suppose no notice appeared before close. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"governance"}},{"id":"r11-mf-r-10","english":"blinding protocol P7 requires the analyst to blind labels before scoring; duty, not inference.","ainglish":"The analyst must-as-rule blind labels before scoring.","question":"Suppose labels were visible during scoring. What follows from this message?","options":["inference mistaken","both","neither","rule breached"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"research"}},{"id":"r11-mf-i-10","english":"lab trace P7 supports that the analyst blinds labels before scoring; inference, no duty.","ainglish":"The analyst must-as-inference blind labels before scoring; evidence: lab trace P7.","question":"Suppose labels were visible during scoring. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"research"}},{"id":"r11-mf-r-11","english":"assignment rule R5 requires the allocator to randomize treatment blocks; duty, not inference.","ainglish":"The allocator must-as-rule randomize treatment blocks.","question":"Suppose blocks followed enrollment order. What follows from this message?","options":["both","neither","rule breached","inference mistaken"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"research"}},{"id":"r11-mf-i-11","english":"assignment log R5 supports that the allocator randomizes treatment blocks; inference, no duty.","ainglish":"The allocator must-as-inference randomize treatment blocks; evidence: assignment log R5.","question":"Suppose blocks followed enrollment order. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"research"}},{"id":"r11-mf-r-12","english":"replication policy D2 requires the replicator to pin every dependency; duty, not inference.","ainglish":"The replicator must-as-rule pin every dependency.","question":"Suppose one dependency was unpinned. What follows from this message?","options":["neither","rule breached","inference mistaken","both"],"answer":"rule breached","settlement_stratum":"must-as-rule","strata":{"form":"must-as-rule","domain":"research"}},{"id":"r11-mf-i-12","english":"build log D2 supports that the replicator pins every dependency; inference, no duty.","ainglish":"The replicator must-as-inference pin every dependency; evidence: build log D2.","question":"Suppose one dependency was unpinned. What follows from this message?","options":["rule breached","inference mistaken","both","neither"],"answer":"inference mistaken","settlement_stratum":"must-as-inference","strata":{"form":"must-as-inference","domain":"research"}},{"id":"r11-mf-cal-01","calibration":true,"english":"The note mentions the amber token, but gives no location.","ainglish":"The note states that the amber token is in locker 27. Control instruction: select exactly \u0027locker 27\u0027.","question":"Where does the note place the amber token?","options":["locker 27","dispatch desk","archive room","not stated"],"answer":"locker 27","strata":{"control":"construct-free-planted-effect"}},{"id":"r11-mf-cal-02","calibration":true,"english":"The note mentions the blue key, but gives no location.","ainglish":"The note states that the blue key is in drawer 14. Control instruction: select exactly \u0027drawer 14\u0027.","question":"Where does the note place the blue key?","options":["dispatch desk","archive room","not stated","drawer 14"],"answer":"drawer 14","strata":{"control":"construct-free-planted-effect"}},{"id":"r11-mf-cal-03","calibration":true,"english":"The note mentions the green seal, but gives no location.","ainglish":"The note states that the green seal is in cabinet 8. Control instruction: select exactly \u0027cabinet 8\u0027.","question":"Where does the note place the green seal?","options":["archive room","not stated","cabinet 8","dispatch desk"],"answer":"cabinet 8","strata":{"control":"construct-free-planted-effect"}},{"id":"r11-mf-cal-04","calibration":true,"english":"The note mentions the silver badge, but gives no location.","ainglish":"The note states that the silver badge is in safe 31. Control instruction: select exactly \u0027safe 31\u0027.","question":"Where does the note place the silver badge?","options":["not stated","safe 31","dispatch desk","archive room"],"answer":"safe 31","strata":{"control":"construct-free-planted-effect"}},{"id":"r11-mf-cal-05","calibration":true,"english":"The note mentions the red folder, but gives no location.","ainglish":"The note states that the red folder is in shelf 22. Control instruction: select exactly \u0027shelf 22\u0027.","question":"Where does the note place the red folder?","options":["shelf 22","dispatch desk","archive room","not stated"],"answer":"shelf 22","strata":{"control":"construct-free-planted-effect"}},{"id":"r11-mf-cal-06","calibration":true,"english":"The note mentions the white card, but gives no location.","ainglish":"The note states that the white card is in box 16. Control instruction: select exactly \u0027box 16\u0027.","question":"Where does the note place the white card?","options":["dispatch desk","archive room","not stated","box 16"],"answer":"box 16","strata":{"control":"construct-free-planted-effect"}}],"models":["falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"],"readers":[{"name":"falcon3-10b-qualification-v7-c8647169c2b9","provider":"ollama","model":"dexagon-falcon3-10b-qualification-v7:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/localhost:11434\/v1","model_digest":"sha256:53c57c624bebfbc119e4dbdae94227d671cc8b000d8cc6aae238c01d7fcc3ad1","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":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},{"name":"olmo2-13b-qualification-v7-cd836509a1a0","provider":"ollama","model":"dexagon-olmo2-13b-qualification-v7:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/localhost:11434\/v1","model_digest":"sha256:71d70c4abc447d98508f4e1698bfd899b54d326666b620b8a0a281b2b2d63f85","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":"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":"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","digest_source":"ollama:\/api\/tags"},{"reader":"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m","digest_source":"ollama:\/api\/tags"}]},"item_counts":{"real":24,"calibration":6},"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":"0b6e71eaf3ed2b63d2599793072937853eeab69b752de03564392436cfda52fe"},"settlement_strata":[{"id":"must-as-rule","weight":1},{"id":"must-as-inference","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":24},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.49","transport":{"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m":{"max_tokens":64,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m":{"max_tokens":64,"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":{"falcon3-10b-qualification-v7-c8647169c2b9":1,"olmo2-13b-qualification-v7-cd836509a1a0":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":"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":2026090311,"items":[{"id":"r11-mf-i-01","stratum":"must-as-inference"},{"id":"r11-mf-i-02","stratum":"must-as-inference"},{"id":"r11-mf-i-03","stratum":"must-as-inference"},{"id":"r11-mf-i-04","stratum":"must-as-inference"},{"id":"r11-mf-i-05","stratum":"must-as-inference"},{"id":"r11-mf-i-06","stratum":"must-as-inference"},{"id":"r11-mf-i-07","stratum":"must-as-inference"},{"id":"r11-mf-i-08","stratum":"must-as-inference"},{"id":"r11-mf-i-09","stratum":"must-as-inference"},{"id":"r11-mf-i-10","stratum":"must-as-inference"},{"id":"r11-mf-i-11","stratum":"must-as-inference"},{"id":"r11-mf-i-12","stratum":"must-as-inference"},{"id":"r11-mf-r-01","stratum":"must-as-rule"},{"id":"r11-mf-r-02","stratum":"must-as-rule"},{"id":"r11-mf-r-03","stratum":"must-as-rule"},{"id":"r11-mf-r-04","stratum":"must-as-rule"},{"id":"r11-mf-r-05","stratum":"must-as-rule"},{"id":"r11-mf-r-06","stratum":"must-as-rule"},{"id":"r11-mf-r-07","stratum":"must-as-rule"},{"id":"r11-mf-r-08","stratum":"must-as-rule"},{"id":"r11-mf-r-09","stratum":"must-as-rule"},{"id":"r11-mf-r-10","stratum":"must-as-rule"},{"id":"r11-mf-r-11","stratum":"must-as-rule"},{"id":"r11-mf-r-12","stratum":"must-as-rule"}],"readers":["falcon3-10b-qualification-v7-c8647169c2b9","olmo2-13b-qualification-v7-cd836509a1a0"],"cells":[{"item_id":"r11-mf-i-01","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-i-01","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"r11-mf-i-02","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-02","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"r11-mf-i-03","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-i-03","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-04","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"r11-mf-i-04","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-i-05","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"r11-mf-i-05","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"r11-mf-i-06","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"r11-mf-i-06","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-07","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-07","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"r11-mf-i-08","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-08","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-i-09","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-09","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-10","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"r11-mf-i-10","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"r11-mf-i-11","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-i-11","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"r11-mf-i-12","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-i-12","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-01","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-01","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-02","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-02","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"r11-mf-r-03","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-r-03","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-04","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-04","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-05","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-05","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"r11-mf-r-06","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-r-06","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"r11-mf-r-07","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-07","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"r11-mf-r-08","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-08","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-09","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-09","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-10","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"r11-mf-r-10","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"r11-mf-r-11","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-11","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-12","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"r11-mf-r-12","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true}],"content_sha256":"8a4d1fbec00ef8bba266d95ceb90de08b1f50f540a90f8d9bd7efc5329325c7e"},"replicates":{"hash":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d","url":"\/api\/v1\/measurements\/fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d"},"replications":[],"replicate":null}