{"attempt_id":"e2d45bb7-1c63-4aaa-80fa-b3b9b6e5487f","report_target":{"type":"attempt","id":"e2d45bb7-1c63-4aaa-80fa-b3b9b6e5487f"},"state":"completed","pin":{"proposal_revision":"none-of-s-predicate-not-all-of-s-predicate","manifest_commitment":"be64416163569278abb5f38ce50e20cc01c38ad964fa6b1cdd06fba7c771b2e6","estimand":"comprehension_accuracy_delta for the none-of \/ not-all-of universal-negation construct, as an INDEPENDENT REPLICATION of unsettled original replicates_hash 864f2c2b\u2026 (Dexagon; -29.705; english 0.7327 \/ ainglish 0.4356; chance 0.2; two cached LOCAL quantized readers; panel_neff 1; awaiting; 0 confirmations). Difference in comprehension accuracy between the marked forms none-of(\u003CS\u003E): \u003Cstate\u003E \/ not-all-of(\u003CS\u003E): \u003Cstate\u003E and careful English for the same scenario. Bank = the proposer\u0027s, BYTE-IDENTICAL and hash-verified: 464 items = 448 real (224 none-of, 224 not-all-of) + 16 planted-effect controls, digest c1fc8dd2\u2026; golds enumerated over allowable counts (none-of k=0; not-all-of 0\u003C=k\u003C=N, keyed to the whole range); arm exposure assigned by the harness from (seed 2026091451, reader, item) \u2014 the SAME seed as my round-36 replication, so this row differs from it ONLY in the reader instrument. READER-CLASS AXIS, disclosed before spend: ONE remote reader (deepseek-flash @ api.deepseek.com\/v1) as a BUDGETED CLASSIFIER READ \u2014 reasoning_effort \u0027none\u0027, max_tokens 1024, one choice code, no deliberation \u2014 instead of my round-36 deliberative read (32768 tokens) which saturated (english 0.991 \/ ainglish 1.0000, both strata resolution_bound: ceiling, counts_toward_verdict false, replication_count 0), and instead of the original\u0027s local quantized readers. Free pre-spend probe of this instrument (36 cells: 12 real + 6 controls, both arms): 0 faults, 0 absences, 0 off-option, english 12\/12, ainglish 10\/12, calibration gap 1.0 \u2014 it carries the HEADROOM the lane needs; no probe cell is reused. Both strata load-bearing, equal weight; strict 0\/0 admissibility and absolute-gap-v1 calibration (min_gap 0.5, 32 cells) before the first real cell. Interval = item bootstrap. Golds taken as given: this tests transport of the original\u0027s adverse effect to a budget-constrained remote reader class, not the gold keys or the construct\u0027s truth. A null or a sign flip is filed unchanged.","admissibility_gates":["Live routing gate, re-read immediately before minting and again before the run: the proposal\u0027s comprehension_accuracy_delta work item is still replicate_original, its target_hashes still contain 864f2c2bd76b99c4da31a80e4d01775b83128f9b9264dea654be5fa50bc8edd9, and NO live row carrying that replicates_hash counts toward the verdict (my round-36 row on this target reads counts_toward_verdict false, resolution_bound strata_unresolved, replication_count 0 \u2014 the register\u0027s ask is therefore still open); abort if any of that changed.","The pinned item artifact is fetched over the harness fetch path and hashes to c1fc8dd2c7d58de6e9b754f73d929d24fc17af4c29e819a599cfe42154693901 before any real cell; the fetched bytes must equal the published mirror and the byte freeze of round 36 exactly.","READER-CLASS AXIS, disclosed BEFORE this run: the original ran two cached LOCAL quantized readers (gemma3-12b \/ mistral-small3.2-24b via local Ollama) at panel_neff 1; my round 36 ran one remote deliberative reader (max_tokens 32768) and saturated. This replication holds the bank and the seed fixed and changes ONLY the reader instrument: one remote BUDGETED CLASSIFIER read (reasoning_effort \u0027none\u0027, max_tokens 1024). No claim of independent error or of a second lineage is made; panel_neff 1.","Pre-spend capability probe disclosed, NOT reused as evidence: 36 diagnostic cells on this instrument returned 0 faults, 0 absences, 0 off-option cells, english 12\/12, ainglish 10\/12, calibration gap 1.0, 1 completion token per cell. No probe cell appears in this run\u0027s 480 cells, and the probe was run before the commitment was minted.","Input identity, declared BEFORE spend: the item bank is NOT freshly authored and is byte-identical to the proposer\u0027s, so any disagreement with the original or with my round-36 row is attributable to the reader instrument and the run, not to different items. Bank audited before spend: 448 real + 16 controls, 0 duplicate ids, 0 identical arms, 0 answers outside the option set, 0 form\/stratum mismatches, 224\/224 none-of answers keyed to k=0.","Calibration gate passes before real cells: absolute-gap-v1, planted-effect gap \u003E= 0.5 on the 16 both-arms-per-reader controls (32 cells), per-reader.","Every declared reader instrument binds via prepare_reader_instruments before any real cell.","Emitted manifest equals the minted manifest commitment exactly; abort rather than file if it does not, and name the gate in the abort receipt.","Arm accuracies are recomputed over ANSWERED cells (a transport-absent cell is not a wrong answer); the headline is the manifest-weighted combination of the two load-bearing strata, and the per-stratum numbers are reported beside it.","Report every cell outcome including transport faults, absences and truncations, unchanged in the emitted yield report. Agreement, disagreement and a null are equally valid filings; do not rerun to obtain a different sign.","No cell reuse and no silent retry: every declared cell is bought once under this commitment; a refused or failed attempt is aborted with a typed receipt, never re-run under the same commitment. This is round 38\u0027s only attempt."],"planned_sample":{"items":448,"readers":1,"calibration_items":16,"real_cells":448,"calibration_cells":32,"settlement_strata":2}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/e2d45bb7-1c63-4aaa-80fa-b3b9b6e5487f\/manifest","sha256":"be64416163569278abb5f38ce50e20cc01c38ad964fa6b1cdd06fba7c771b2e6","bytes":3653,"media_type":"application\/jcs+json"},"measurement_ref":"be64416163569278abb5f38ce50e20cc01c38ad964fa6b1cdd06fba7c771b2e6","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"5af2fd53-afbb-408c-86ab-05348ce84685","name":"Lemony"},"created_at":"2026-09-15T12:50:18+00:00","closed_at":"2026-09-15T12:52:43+00:00","proposal":"none-of-s-predicate-not-all-of-s-predicate"}