{"attempt_id":"dcdbafa8-9664-4267-ae94-919c612e899e","report_target":{"type":"attempt","id":"dcdbafa8-9664-4267-ae94-919c612e899e"},"state":"completed","pin":{"proposal_revision":"must-as-rule-must-as-inference-does-must-impose-a-requiremen","manifest_commitment":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d","estimand":"Percentage-point exact-answer accuracy difference, registered compact form minus complete careful-English mapping, over 64 frozen fresh items for must-as-rule \/ must-as-inference; equal-weight mean of the separately reported form strata (must-as-rule, must-as-inference). Primary interpretation is non-inferiority at -5 percentage points; absolute arms, per-reader results, intervals, calibration, yield, and every stratum remain visible.","admissibility_gates":["the live proposal remains current at measured stage and still names an original comprehension_accuracy_delta as its primary evidence-completion action immediately before mint","the published answer-bearing item array hashes to 04a2ccb275d7ef9d865765cf37d1c1a2c3f9cd7c2a2b0d227107421ff9dc087d and contains exactly 64 scientific plus 16 calibration items","every scientific English arm states the complete registered careful-English meaning; no bare ambiguous comparator enters the scalar","both named local reader artifacts match their declared Ollama digests and run statelessly at temperature 0 with the frozen seed and opaque-choice output","the construct-free planted-effect calibration executes first in both arms for each reader and must show an explicit-minus-unresolved accuracy gap of at least 0.5","each real item names one committed equal-weight settlement stratum, and every form remains separately visible","no reader receives repository access, retrieval, conversation history, or a register definition beyond the presented cell","zero response-bound truncations and a passing full-cell-yield guard are required; transport or format failure produces a typed abort and no retry","every finite supportive, adverse, null, floor-bound, or ceiling-bound outcome is filed exactly once","a settlement-bearing replication must come from a different principal with a wholly fresh complete item manifest","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":{"comparison":"registered compact form versus complete careful-English mapping","scientific_items":64,"calibration_items":16,"readers":2,"reader_families":["Mistral Small 3.2 24B","Gemma 3 12B"],"panel_neff":2,"real_cells":128,"calibration_cells":64,"settlement_strata":{"must-as-inference":32,"must-as-rule":32},"noninferiority_margin_pp":-5,"sdk_version":"0.2.48","source_commit":"d3545ec78b4c7658f3296ced80ff47a22c722529","handoff_only":false}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/dcdbafa8-9664-4267-ae94-919c612e899e\/manifest","sha256":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d","bytes":4088,"media_type":"application\/jcs+json"},"measurement_ref":"fa10a69200a49d993f82da7871741b4c3bb3cf6e32cd090322cb3a39f3f0f50d","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"created_at":"2026-09-02T11:25:10+00:00","closed_at":"2026-09-02T11:27:07+00:00","proposal":"must-as-rule-must-as-inference-does-must-impose-a-requiremen"}