{"attempt_id":"89622ec3-f8ab-4cfa-97c0-dd5f520cad5d","report_target":{"type":"attempt","id":"89622ec3-f8ab-4cfa-97c0-dd5f520cad5d"},"state":"completed","pin":{"proposal_revision":"value-unknown-value-none-value-redacted-redactor-ref-value","manifest_commitment":"b8237f69f3e30b7e2fb8605a92403e79057cbb6ca1db87ed76e32d1207053ae9","estimand":"Percentage-point exact-answer accuracy difference, registered compact form minus its committed per-item comparator, over 160 frozen fresh items for value-unknown \/ value-none \/ value-redacted \/ value-inapplicable; equal-weight mean of separately reported strata (value-unknown, value-none, value-redacted, value-inapplicable). All four strata compare the compact semantic meta-value with its complete careful-English mapping; primary interpretation is non-inferiority at -5 percentage points with each form visible. 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 submit_original for comprehension_accuracy_delta immediately before mint","the published answer-bearing item array hashes to 106ca11a677a6e6a49f86e9f64234ef56e8828ceda56ff7957efac6bb87a5ffc and contains exactly 160 scientific plus 16 calibration items","all scientific questions are held-out exact semantic-consequence questions and contain none of the target marker strings","each careful-English comparator states the complete target meaning; each bare comparator is balanced across opposed hidden intentions and is never presented as a complete mapping","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 and comparator class 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","the filing principal is distinct from the proposal\u0027s original proposer","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 committed per-item comparator","scientific_items":160,"calibration_items":16,"readers":2,"reader_families":["Mistral Small 3.2 24B","Gemma 3 12B"],"panel_neff":2,"real_cells":320,"calibration_cells":64,"settlement_strata":{"value-inapplicable":40,"value-none":40,"value-redacted":40,"value-unknown":40},"noninferiority_margin_pp":-5,"sdk_version":"0.2.50","source_commit":"8c5d267e5a7249e4221487ccceeb66bfc78686c5"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/89622ec3-f8ab-4cfa-97c0-dd5f520cad5d\/manifest","sha256":"b8237f69f3e30b7e2fb8605a92403e79057cbb6ca1db87ed76e32d1207053ae9","bytes":4251,"media_type":"application\/jcs+json"},"measurement_ref":"b8237f69f3e30b7e2fb8605a92403e79057cbb6ca1db87ed76e32d1207053ae9","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":"2026-09-02T21:38:53+00:00","closed_at":"2026-09-02T21:42:49+00:00","proposal":"value-unknown-value-none-value-redacted-redactor-ref-value"}