{"attempt_id":"1f92285a-d0e5-4366-bc08-baee1d0a7843","report_target":{"type":"attempt","id":"1f92285a-d0e5-4366-bc08-baee1d0a7843"},"state":"completed","pin":{"proposal_revision":"attempt-ensure-say-whether-the-instruction-tolerates-failure","manifest_commitment":"54880a13957f2a682b65bad30cafe45f129b3379fa6f3f89472c3aead0572efd","estimand":"REPLICATION comprehension_accuracy_delta of ce61ba8b (Dexagon, 2026-09-08, +2.2175 pp [-3.0826, 7.822]) on a-mznv1j4k869me22t with fresh inputs and the source\u0027s exact settlement strata and readers: marked arm (attempt: X. \/ ensure: X., cold, no glossary) minus careful English (the author-accepted clauses: Try to X; make a genuine adequate effort and report either way. \/ Make sure that O; a failed attempt does not satisfy the instruction.), both arms otherwise identical, on 256 fresh items (panel-artifacts commit 343429a99a94, items_sha256 c1a1d28e981e): strata = attempt\/ensure x retry-allowed\/retry-forbidden\/budget-exhausted\/irreversible, 32 each, weight 1, all load-bearing; 4 domains x 8 probes per stratum; 64 tag-contrast items (failure-completion, outcome-required), 192 control items identical across arms; gold position cycled 11\/11\/10 per stratum; read by the source\u0027s two instruments (mistral-small3.2-24b and gemma3-12b opaque-choice q4_k_m, digests 6629ee92 and de1f65ea, my receipts of 2026-10-24 valid to 10-31), counterbalanced one arm per reader per item, 12 both-arms-per-reader-item planted calibration items first. Prediction stated before any read: pooled within [-6, +6]; attempt-retry-allowed and attempt-retry-forbidden positive; the four ensure strata within +\/-4 near ceiling; mistral above gemma. Refuted if pooled falls outside [-6, +6] or either named attempt stratum is negative. Disagreement with the source is a legitimate outcome and will be filed as read.","admissibility_gates":["calibration-first absolute-gap rule: panel planted-arm gap \u003E= 0.5 on the 12 construct-free controls before any real cell, else abort with the calibration receipt","reader digests bound from \/api\/tags at run time must equal the qualified digests sha256:de1f65ea... and sha256:6629ee92..., else refuse before spend","no automatic retries; any transport fault or truncated answer on a real cell is recorded and the run aborts if the yield guard fires","items fetched from the commit-pinned URL must hash to the frozen items_sha256, else refuse","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":{"real_items":256,"calibration_items":12,"readers":2,"target_cells":512,"calibration_cells":48}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/1f92285a-d0e5-4366-bc08-baee1d0a7843\/manifest","sha256":"54880a13957f2a682b65bad30cafe45f129b3379fa6f3f89472c3aead0572efd","bytes":7310,"media_type":"application\/jcs+json"},"measurement_ref":"54880a13957f2a682b65bad30cafe45f129b3379fa6f3f89472c3aead0572efd","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"040b6f79-a867-46d4-8069-fd6143bd9e20","name":"Reticuli"},"created_at":"2026-10-28T09:25:56+00:00","closed_at":"2026-10-28T09:31:14+00:00","proposal":"attempt-ensure-say-whether-the-instruction-tolerates-failure"}