{"attempt_id":"3d7e6c3e-e49b-46ce-b12e-37baa83bac87","report_target":{"type":"attempt","id":"3d7e6c3e-e49b-46ce-b12e-37baa83bac87"},"state":"completed","pin":{"proposal_revision":"you-one-you-all-say-whether-you-addresses-one-recipient-or-t","manifest_commitment":"990939277f143a83c9bb9b7d659a61084e5f32ceecec9156f3452dc59805baca","estimand":"Original post-ratification flagship carrier for you-all: percentage-point difference in exact held-out consequence recovery, the compact you-all arm minus the complete registered careful-English mapping for you-all, over 100 fresh meaning-matched pairs. The standalone primary interpretation is non-inferiority at -5 percentage points. Absolute arms, the 95% interval, resolution bound, calibration, yield, transport, reader, and resample-down receipts are all retained.","admissibility_gates":["the public 100+8 carrier has SDK canonical-items sha256 fdb3718eaf56951d9b63e494a8477781cfe7fce61328fa2a74042fb96bd8d889","the answer-bearing carrier was frozen at public commit cb4897a0418e4e6ded4e5ebfb7d6c3779cd07d9f before attempt mint or reader spend","every scientific English arm is the marker\u0027s complete careful-English meaning for the tested consequence; ambiguous bare English is absent from the scalar","every held-out question is answered through opaque A\/B\/C codes; a reader never has to echo an answer label","the two local reader weight editions are verified against their declared Ollama digests before spend and are distinct model families","the construct-free calibration runs first in both arms for every reader and must produce a planted-arm gap of at least 0.5","the dedicated loopback reader is idle and GPU 0 has at least 20,000 MiB free before the campaign starts","zero response-bound truncations and a passing cell-yield guard are required for the preregistered clean-run manifest to reconcile","every finite supportive, adverse, null, floor-bound, or ceiling-bound result is filed exactly once; no outcome retry is permitted","a different-principal confirmation must use wholly fresh answer-bearing inputs; this original cannot confirm itself","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)"],"planned_sample":{"form":"you-all","scientific_items":100,"calibration_items":8,"readers":2,"reader_families":["Mistral Small 3.2 24B","Gemma 3 12B"],"panel_neff":2,"real_cells":200,"calibration_cells":32,"noninferiority_margin_pp":-5,"sdk_version":"0.2.35"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/3d7e6c3e-e49b-46ce-b12e-37baa83bac87\/manifest","sha256":"990939277f143a83c9bb9b7d659a61084e5f32ceecec9156f3452dc59805baca","bytes":3266,"media_type":"application\/jcs+json"},"measurement_ref":"990939277f143a83c9bb9b7d659a61084e5f32ceecec9156f3452dc59805baca","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"created_at":"2026-08-25T06:51:00+00:00","closed_at":"2026-08-25T06:53:24+00:00","proposal":"you-one-you-all-say-whether-you-addresses-one-recipient-or-t"}