{"attempt_id":"0750a024-9b42-4842-a814-4f8c88eeb37b","report_target":{"type":"attempt","id":"0750a024-9b42-4842-a814-4f8c88eeb37b"},"state":"completed","pin":{"proposal_revision":"none-of-s-predicate-not-all-of-s-predicate","manifest_commitment":"a6f513d15c774e31364b22ac5bc68457b3c37453ae5f6d1aa92151ce04387ce2","estimand":"comprehension_accuracy_delta for the none-of \/ not-all-of universal-negation construct, as an INDEPENDENT, DIFFERENT-INPUT replication of the retained consequence original 03604fc1 (Dexagon; -34.810; english 0.8734 \/ ainglish 0.5253; two cached LOCAL quantized readers, panel_neff 1; awaiting, 0 replications). Difference in comprehension accuracy between the marked forms none-of(\u003CS\u003E): \u003CP\u003E \/ not-all-of(\u003CS\u003E): \u003CP\u003E and the proposal\u0027s careful-English mapping (No member of S satisfies P \/ At least one member of S does not satisfy P) over the SAME scenarios. Bank: FRESHLY AUTHORED and hash-pinned (bdf3bfd2\u2026; 2,256 items = 2,240 real, 1,120 per stratum, + 16 planted-effect controls) at items_url; fresh domains, members, properties and wording, 0 shared scenario 8-grams with either source bank; every gold produced by the independent derivation that reproduced the retained bank\u0027s 2,240 filed keys with 0 mismatches. NEW QUESTION, stated before spend: does the consequence loss transfer to fresh inputs and to a hosted, non-quantized reader class? READER CLASS, declared before spend: ONE remote reader (deepseek-flash @ api.deepseek.com\/v1) as a BUDGETED CLASSIFIER READ (reasoning_effort none, max_tokens 1024) - the class with demonstrated headroom in round 38 - instead of the original\u0027s two cached local quantized readers. Arm exposure is harness-assigned from (seed 20260916, reader, item); both strata load-bearing at equal weight; strict 0\/0 admissibility; planted-effect calibration (16 controls, both arms, gap \u003E= 0.5, recovered \u003E= 0.875) before the first real cell. Golds are taken as given: this tests input and reader-population generalization of the original\u0027s adverse effect, not the construct\u0027s truth. Agreement, disagreement and a null are equally valid filings; a reader-panel result does not establish token savings, human comprehension or performance outside the declared reader population.","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 03604fc182efb10175bb4598b1cff40fd606708e7a0fb8aba66e94800af92d43, and NO live row carrying that replicates_hash counts toward the verdict; abort if any of that changed.","Bank identity: the pinned fresh artifact is fetched over the harness fetch path and hashes to bdf3bfd2462e27cfb3f3d2ac8f42410876e411b66471fd2d19da99ed0394916c before any real cell; the fetched bytes must equal the published mirror exactly (2,256 items; 1,120 real per stratum; 16 controls).","Input disjointness, declared BEFORE spend: the bank is freshly authored for this run - new domains, members, properties, scenario wording and probe wording - and shares ZERO scenario 8-grams with either source bank (the retired primary bank c1fc8dd2\u2026 and the consequence bank a8f6e877\u2026). The marked forms, the proposal\u0027s careful-English mapping and the five probe semantics are held fixed by the protocol; arm exposure is harness-assigned from (seed 20260916, reader, item).","Key derivation, disclosed: every gold is produced by an independent implementation of the mapping (none-of permits k=0 only; not-all-of permits 0 \u003C= k \u003C N) x the five probe semantics x coverage; the same implementation reproduces the retained consequence bank\u0027s 2,240 filed keys with 0 mismatches, and its output is audited against this bank before spend (0 mismatches).","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. This replication uses ONE remote hosted reader (deepseek-flash @ api.deepseek.com\/v1) as a 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: 28 diagnostic cells on this instrument (20 real items in the arm the filed run will NOT read + 4 ad-hoc controls in both arms) returned 0 faults, 0 absences, 0 off-option cells, control gap 1.0, run before the commitment was minted. No probe cell appears in this run\u0027s 2,272 cells.","Calibration gate passes before real cells: headroom-relative-v1, planted-effect gap \u003E= 0.5 and recovered \u003E= 0.875 on the 16 both-arms-per-reader controls (32 cells), per-reader.","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, with per-stratum item-bootstrap intervals attached to stratum_results.","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 43\u0027s only attempt."],"planned_sample":{"items":2240,"readers":1,"calibration_items":16,"real_cells":2240,"calibration_cells":32,"settlement_strata":2}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/0750a024-9b42-4842-a814-4f8c88eeb37b\/manifest","sha256":"a6f513d15c774e31364b22ac5bc68457b3c37453ae5f6d1aa92151ce04387ce2","bytes":3763,"media_type":"application\/jcs+json"},"measurement_ref":"a6f513d15c774e31364b22ac5bc68457b3c37453ae5f6d1aa92151ce04387ce2","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":"2026-09-16T13:07:01+00:00","closed_at":"2026-09-16T13:15:57+00:00","proposal":"none-of-s-predicate-not-all-of-s-predicate"}