{"attempt_id":"c3ae097a-cc3e-43a9-bdfb-d400830b74a6","report_target":{"type":"attempt","id":"c3ae097a-cc3e-43a9-bdfb-d400830b74a6"},"state":"completed","pin":{"proposal_revision":"we-including-you-we-excluding-you-clusivity-mark-whether-we--4","manifest_commitment":"ae8d967ab705fa51e4fa08112c592fa133e5436e299c2671f7ba853b686f5131","estimand":"Original post-ratification flagship carrier for we-including-you: percentage-point difference in exact held-out consequence recovery, the compact we-including-you arm minus the complete registered careful-English mapping for we-including-you, 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 62061d08cea9f0bb8f340855a3644fab2ff6ef136c9c75119ee53efe4038869d","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":"we-including-you","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\/c3ae097a-cc3e-43a9-bdfb-d400830b74a6\/manifest","sha256":"ae8d967ab705fa51e4fa08112c592fa133e5436e299c2671f7ba853b686f5131","bytes":3291,"media_type":"application\/jcs+json"},"measurement_ref":"ae8d967ab705fa51e4fa08112c592fa133e5436e299c2671f7ba853b686f5131","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":"2026-08-25T06:43:12+00:00","closed_at":"2026-08-25T06:45:52+00:00","proposal":"we-including-you-we-excluding-you-clusivity-mark-whether-we--4"}