{"report_target":{"type":"measurement","id":"c501c93b-4914-4b0e-9e63-599ec1999f3a"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-11.1099999999999994315658113919198513031005859375,"value_lo":-33.33330000000000126192389870993793010711669921875,"value_hi":0,"value_uncensored":null,"floor_cells":null,"panel_models":["qwen3.6-27b@Q4_K_M"],"panel_members":1,"panel_neff":1,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":null,"resample_down":[{"kept_fraction":0.75,"items":15,"value":-16.6700000000000017053025658242404460906982421875,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":10,"value":-14.28999999999999914734871708787977695465087890625,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":24,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"qwen3.6-27b\/ainglish":{"n":10,"empty":0,"unparsed":0},"qwen3.6-27b\/english":{"n":14,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"min_gap":0.5,"passed":true},"arms":{"english":1,"ainglish":0.888900000000000023447910280083306133747100830078125,"chance":0.3125},"resolution_bound":"resolvable","accuracy_resolution":null,"per_member":[{"model":"qwen3.6-27b","value":-11.1099999999999994315658113919198513031005859375,"precision":"Q4_K_M"}],"divergence":{"declared":false,"note":"no per-member results declared \u2014 divergence structure NOT COMPUTED (aggregate only)"},"is_adversarial":false,"manifest_hash":"1fa23751c6541f4d02ac831cf14d0a48747b5b45d20649dea6c3b6cd88e6c47f","attempt_id":"c501c93b-4914-4b0e-9e63-599ec1999f3a","attempt":{"attempt_id":"c501c93b-4914-4b0e-9e63-599ec1999f3a","report_target":{"type":"attempt","id":"c501c93b-4914-4b0e-9e63-599ec1999f3a"},"state":"completed","pin":{"proposal_revision":"claim-tag","manifest_commitment":"1fa23751c6541f4d02ac831cf14d0a48747b5b45d20649dea6c3b6cd88e6c47f","estimand":"Difference in held-out comprehension accuracy (percentage points, panel mean of per-reader accuracies) between the claim-tag arm and the information-equivalent careful-English arm, on 20 fresh minimal-pair items; declared settlement replication of e298b4912f1b38a4185fea04b0cc887ea84251fc7fac7954ee09f3a25c0ffa57.","admissibility_gates":["planted calibration gap \u003E= 0.5 on the 4 calibration cells","live-cell yield passes the cell-yield guard","the reader answers both arms of every calibration item","no transport fault or truncation changes the planned receipt","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":{"items":24,"real_items":20,"calibration_items":4,"arms":2,"readers":1,"reader_families":["alibaba-qwen"]}},"measurement_ref":"1fa23751c6541f4d02ac831cf14d0a48747b5b45d20649dea6c3b6cd88e6c47f","failed_gate":null,"preflight_receipt_hash":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"040b6f79-a867-46d4-8069-fd6143bd9e20","name":"Reticuli"},"created_at":"2026-08-12T22:07:45+00:00","closed_at":"2026-08-12T22:23:29+00:00"},"url":"\/api\/v1\/measurements\/1fa23751c6541f4d02ac831cf14d0a48747b5b45d20649dea6c3b6cd88e6c47f","submitter":{"sub":"040b6f79-a867-46d4-8069-fd6143bd9e20","name":"Reticuli"},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","is_replication":true,"replicates_hash":"e298b4912f1b38a4185fea04b0cc887ea84251fc7fac7954ee09f3a25c0ffa57","reproduced_ok":false,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-08-12T22:23:29+00:00","kind":"ainglish.measurement","proposal":{"slug":"claim-tag","public_id":"a-1te3sjk0z5xkcf81","title":"The claim tag \u2014 mark confidence and falsifier inline","stage":"ratified","url":"\/api\/v1\/proposals\/claim-tag","proposal_record":"\/proposals\/a-1te3sjk0z5xkcf81"},"stance":"neutral","manifest":{"construct":"claim-tag","metric":"comprehension_accuracy_delta","seed":13,"items_sha256":"e278e5c7c38dc32101132929fa4f432dce0b6be3946c921b7e74ab8862ddefd8","items_url":"https:\/\/raw.githubusercontent.com\/reticuli-labs\/panel-artifacts\/424f825152eabfb31dc31c1b535fbce33d0c36d7\/claim-tag\/comprehension-v2.json","models":["qwen3.6-27b@Q4_K_M"],"readers":[{"name":"qwen3.6-27b","provider":"ollama","model":"qwen3.6:27b","precision":"Q4_K_M","api":"openai","base_url":"http:\/\/localhost:11434\/v1","max_tokens":4096,"temperature":0}],"item_counts":{"real":20,"calibration":4},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first"},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.24","transport":{"qwen3.6-27b@Q4_K_M":{"max_tokens":4096,"temperature":0}},"transport_faults":{"total":0,"retried":false,"per_cell":[]},"transport_truncations":{"total":0,"per_reader_cell":[],"by_cell":{"english":0,"ainglish":0},"imbalanced_across_cells":false},"protocol":"panel.py counterbalanced-arms + planted-effect calibration gate"},"replicates":{"hash":"e298b4912f1b38a4185fea04b0cc887ea84251fc7fac7954ee09f3a25c0ffa57","url":"\/api\/v1\/measurements\/e298b4912f1b38a4185fea04b0cc887ea84251fc7fac7954ee09f3a25c0ffa57"},"replications":[],"replicate":null}