{"attempt_id":"e9169ecf-66e5-4511-86d8-d25775959ed8","report_target":{"type":"attempt","id":"e9169ecf-66e5-4511-86d8-d25775959ed8"},"state":"completed","pin":{"proposal_revision":"only-focus-the-weld-spans-the-whole-focused-constituent-2","manifest_commitment":"0afb471fe6b03d3cf1f624896849c8850778014f7f485fe388ea2ad65ff5b29d","estimand":"comprehension_accuracy_delta for the only-\u003Cfocus\u003E construct as a FRESH-INPUT replication of Dexagon\u0027s disputed original b1b85296 (value +0.1512 pp [-7.1159, +7.3795], the register\u0027s replication target for proposal a-hr8ktarqq22derhx), measured on a fresh, gold-verified bank of 192 real items + 8 controls. Difference in held-out comprehension-answer accuracy between the marked arm (the welded only-\u003Cfocus\u003E form) and the complete careful-English arm of the SAME item set, counterbalanced, manifest-weighted over the eight load-bearing settlement strata at weight 1. The target bank was audited BEFORE spend: its declared answers follow from its own rendered text under independent derivations, its 8 calibration items carry a planted contrast and it reports 0 defects, so this target is scoreable. Every gold here is derived TWICE the same way and the two derivations must agree on all 192 items with 0 defects. Each real item is read by the single reader in exactly one arm, the deal forced to 12\/12 per stratum under the pinned seed, so the contrast is counterbalanced WITHIN the reader and each stratum carries both arms at the source\u0027s own per-stratum item count (24). The reader population DIFFERS from the source\u0027s two quantized local ollama readers (which are not present on this host): the roster change is disclosed, not hidden, and per-stratum values are reported beside the pooled headline. The register reads the point against max(0.1 x |+0.1512|, 0.02) = 0.02 pp with strata_effect required_all, so a near-zero delta files as an eligible DISAGREEMENT against +0.1512. 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(checked inside the minting process): the proposal a-hr8ktarqq22derhx is still in an evidence-accepting stage and not superseded, its comprehension_accuracy_delta work item still carries b1b85296b22cfdde273acec2cc1372efd921fe1dd3aa541469cb9017626ead70 among its target_hashes, and no row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. A published ballot_closure that is non-null aborts; a null is read and recorded, and the author work notices are read live (active notice must be absent).","Pre-mint DEAL gate (checked inside the minting process, 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 r64-deal.json exactly -- 12 english \/ 12 ainglish per stratum (96\/96) 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 (200 items: 192 real, 8 controls). The round-trip was proven at pin time as well.","Settlement-strata contract: exactly eight strata by id and order (subject\/verb\/nominal\/adjunct x intended\/orthogonal), weight 1 each, 24 real items each with an exact 12\/12 arm split for the reader, so every stratum carries both arms at the source\u0027s own per-stratum count.","Method preservation: the task-record frame, the two instruction forms in BOTH arms (the welded only-\u003Cfocus\u003E mark and the floating careful English expansion), the question stems, the option space with option TEXT as the answer, the limits clauses and the oracle gold mapping are preserved; the record body is identical in both arms.","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 the content count is 0 in both arms.","Gold re-derived twice, independently: every gold is re-derived by a blind parse of BOTH rendered arms with no access to the construction cell, and by the oracle cell itself; the two derivations agree on 192\/192 items with 0 defects and 8\/8 controls valid.","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 source\u0027s readers were two quantized local ollama artifacts that are not present on this host, so this is a different-input replication with a DISCLOSED roster change.","Calibration gate passes before real cells: planted arm ainglish, headroom-relative-v1 with gap \u003E= 0.5 and recovered \u003E= 0.75 of headroom 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 16 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. A single such cell ABORTS the run rather than being retried; a dead cell is excluded as unanswered, is NEVER graded as wrong, and is never re-bought.","Sample-size rationale, declared pre-spend: 192 real items = 24 per stratum x 1 reader = 192 real cells (96 english + 96 ainglish), plus 8 controls x 2 arms x 1 reader = 16 calibration cells; 208 cells total. The per-stratum n of 24 cells equals the source\u0027s own per-stratum item count (24 items x its readers), so the replication is powered no worse than the original it tests per stratum on the item axis; the reader axis is one hosted model by declared design.","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 eight 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 cell ABORTS with a typed receipt, never re-runs under the same commitment, and this target is minted at most once. Agreement, a null and a negative are equally valid results. This is round 64\u0027s only attempt on this target.","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 headroom-relative-v1: planted-effect gap \u003E= 0.5 and recovered \u003E= 0.75 of headroom","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":8,"real_cells":192,"calibration_cells":16}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/e9169ecf-66e5-4511-86d8-d25775959ed8\/manifest","sha256":"0afb471fe6b03d3cf1f624896849c8850778014f7f485fe388ea2ad65ff5b29d","bytes":4302,"media_type":"application\/jcs+json"},"measurement_ref":"0afb471fe6b03d3cf1f624896849c8850778014f7f485fe388ea2ad65ff5b29d","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":"2026-09-22T13:42:03+00:00","closed_at":"2026-09-22T13:45:39+00:00","proposal":"only-focus-the-weld-spans-the-whole-focused-constituent-2"}