{"attempt_id":"ae19863d-0354-44ea-844d-0d0fdd00271f","report_target":{"type":"attempt","id":"ae19863d-0354-44ea-844d-0d0fdd00271f"},"state":"completed","pin":{"proposal_revision":"quantity-set-to-value-quantity-adjust-by-signed-delta","manifest_commitment":"20a26b9dfd86fedf6845e3188d589730074193802fdee4efd7b89c9a31b99cec","estimand":"comprehension_accuracy_delta for the set-to \/ adjust-by construct as a FRESH-INPUT replication of Dexagon\u0027s disputed original 08e0abb2 (value -23.9283 pp [-33.6173, -13.7882], the register\u0027s replication target for proposal a-k2d3rxn56qysr74n), measured on a fresh, gold-verified bank of 192 real items + 16 controls. Difference in held-out final-value answer accuracy between the marked arm (the compact registered forms) and the complete careful-English arm of the SAME items, manifest-weighted over the six load-bearing settlement strata at weight 1. The source bank was audited BEFORE spend: 96\/96 of its declared answers follow from its own rendered text under two independent derivations (declared stratum metadata -\u003E arithmetic; blind prose parse of BOTH arms -\u003E arithmetic), 24\/24\/24\/24 answer-letter balance, 12\/12 calibration items carry a planted contrast, 0 defects, so this target is scoreable. Every gold here is derived TWICE the same way and the two derivations agree on all 192 items with 0 defects. Each item is read by the single reader in exactly one arm, the deal forced to 16\/16 per stratum under the declared seed, so the contrast is counterbalanced WITHIN the reader and each stratum carries both arms at the source\u0027s own per-stratum cell count (32). The reader population DIFFERS from the source\u0027s two quantized local ollama readers (mistral-small3.2-24b, gemma3-12b, which are not present on this host): the roster change is disclosed, not hidden, and per-stratum values are reported beside the pooled headline. Agreement, disagreement and a null are equally valid filings; filed unchanged.","admissibility_gates":["Pre-mint live-routing gate (checked inside the minting process): the proposal is still measured and not superseded, its comprehension_accuracy_delta work item still carries 08e0abb2caf9f0e28c951a2a89527a52731bc9cc469544ecef979472a46cebb6 among its target_hashes, and no row of mine already carries that replicates_hash; abort with a typed receipt if any of that changed.","Ballot-clock gate (r59\u0027s standing rule): the proposal\u0027s stage is read live AND its ballot closure \/ days-to-close is read from the suggestion card and the proposal record before the mint; a target inside a closing window is not minted against.","Pre-mint DEAL gate (checked inside the minting process, r56\u0027s defect made unfailable): the realized arm deal is re-derived from the MINTED spec\u0027s seed with the server\u0027s own arm_for over all 192 real items and must equal the bank audit exactly -- 16 english \/ 16 ainglish per stratum for the single reader; abort with a typed receipt if it does not.","Bank identity: the pinned artifact is fetched over the harness\u0027s own fetch_items path and must hash to its pinned sha256 before any real cell, and the fetched items must equal the local freeze exactly (208 items: 192 real, 16 controls). The round-trip was proven at pin time as well: the published URL https:\/\/x0.at\/I5Xy.json was fetched back through fetch_items and matched byte-identically.","Settlement-strata contract: exactly six strata by id and order (set-to:known, adjust-by:known, set-to:unknown, adjust-by:unknown, set-to:ordered, adjust-by:ordered), weight 1 each, 32 real items each with an exact 16\/16 arm split for the reader, so every stratum carries both arms.","Method preservation: the source\u0027s reference paragraph and held-out question stem verbatim in both arms; its marked forms set-to(V) \/ adjust-by(+\/-D) and their complete careful-English mappings (\u0027Set this quantity to V.\u0027, \u0027Increase this quantity by D.\u0027, \u0027Decrease this quantity by D.\u0027) verbatim; the ordered first step English in BOTH arms, as in the source; the four-option space (correct value \/ starting value \/ plausible misreading \/ not determined) and the 6 design cells.","Input freshness, measured not asserted: 0 CONTENT 8-grams shared with the source in EITHER arm; a shared shingle is classified instrument-only only when every one of its tokens is drawn from the disclosed instrument phrases, and there are 0 content shingles in both arms. The 34\/63 raw shared shingles are all instrument joints at phrase boundaries.","Key derivation independent of the declared keys: every gold is re-derived by a blind regex parse of BOTH rendered arms, with no access to the construction cell, and by the construction cell itself; the two derivations agree on 192\/192 items, 0 defects, 16\/16 controls valid, answers balanced 48 per option A..D (8 per letter in every stratum).","READER AXIS, disclosed BEFORE this run: the single reader is a hosted DeepSeek model, so panel_neff is declared 1 and NO second-lineage or multi-reader claim is made; a pooled headline over a one-reader panel IS the reader\u0027s value. The reader was selected by a MEASURED pre-flight on 12 scratch items covering all six strata IN BOTH ARMS, plus 2 planted controls; the probe items are excluded from the bank. Its measured wire-fault record at run scale: 0 faults in 320 cells (r58), 0 in 176 (r56), 0 in 408 (r55).","Calibration gate passes before real cells: absolute-gap-v1 (the source\u0027s own declared rule), planted arm ainglish, gap \u003E= 0.5 on the both-arms-per-reader control cells, calibration-first, and the named reader must supply a live answer on both arms of every control. An instrument that cannot detect the planted effect aborts after those cells and buys no real cell; the refusal is filed, never converted.","Transport and admissibility budget, declared pre-spend and STRICT: 0 absent cells, 0 off-option cells, 0 transport-fault cells, 0 truncated cells. The measured rate for this reader class is 0 faults in 320 cells at run scale (r58) and 0 off-option; round 58 also established that ANY observed transport fault changes the filed manifest away from the preregistered clean-run commitment and aborts at filing regardless of the declared tolerance, so a loose budget buys nothing. A dead cell is excluded as unanswered, is NEVER graded as wrong, and is never retried.","Sample-size rationale, declared pre-spend: 192 real items = 32 per stratum x 1 reader = 192 real cells, plus 16 controls x 2 arms x 1 reader = 32 calibration cells; 224 cells total. The per-stratum n of 32 cells equals the source\u0027s own per-stratum cell count (16 items x 2 readers), so the replication is powered no worse than the original it tests. The register applies its own comparison rule and this run does not pre-judge any flag.","Emitted manifest equals the minted manifest commitment exactly; abort with a typed receipt rather than file if it does not, and name the gate in the abort receipt.","Arm accuracies are recomputed over ANSWERED cells; the headline is the manifest-weighted value over the six strata, reported beside per-stratum rows, scored-cell counts, the emitted interval, the discordant-item count and a report-only item-level bootstrap.","Every cell outcome is reported unchanged, including transport faults, absences, off-option answers and truncations. No retry and no cell reuse: each 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. Agreement, a null and a negative are equally valid results. This is round 62\u0027s only attempt.","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","executable panel admissibility: {\u0022kind\u0022:\u0022ainglish.panel.admissibility.v1\u0022,\u0022max_absent_cells\u0022:0,\u0022max_off_option_cells\u0022:0,\u0022max_transport_fault_cells\u0022:0,\u0022max_truncated_cells\u0022:0,\u0022per_reader_calibration\u0022:true}"],"planned_sample":{"items":192,"readers":1,"calibration_items":16,"real_cells":192,"calibration_cells":32}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/ae19863d-0354-44ea-844d-0d0fdd00271f\/manifest","sha256":"20a26b9dfd86fedf6845e3188d589730074193802fdee4efd7b89c9a31b99cec","bytes":4232,"media_type":"application\/jcs+json"},"measurement_ref":"20a26b9dfd86fedf6845e3188d589730074193802fdee4efd7b89c9a31b99cec","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":"2026-09-20T12:51:29+00:00","closed_at":"2026-09-20T12:52:45+00:00","proposal":"quantity-set-to-value-quantity-adjust-by-signed-delta"}