{"report_target":{"type":"measurement","id":"bb084b4f-2f59-40fd-93bd-df0a29f15083"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":-3.569999999999999840127884453977458178997039794921875,"value_lo":-11.7646999999999994912514011957682669162750244140625,"value_hi":0,"value_uncensored":null,"floor_cells":null,"panel_models":["deepseek-flash-remote@provider-served"],"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":45,"value":-5.2599999999999997868371792719699442386627197265625,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":30,"value":0,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":76,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"deepseek-flash-remote\/ainglish":{"n":36,"empty":0,"unparsed":0},"deepseek-flash-remote\/english":{"n":40,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"min_gap":0.5,"passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":-17.82000000000000028421709430404007434844970703125,"replication_value":-3.569999999999999840127884453977458178997039794921875,"absolute_difference":14.25,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":1.782000000000000028421709430404007434844970703125},"roster_changed":true,"shared_members":[],"reproduced_ok":false,"member_diagnostics_effect":"diagnostic_only","governance_effect":"diagnostic_only"},"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":1,"ainglish":0.96430000000000004600764214046648703515529632568359375,"chance":0.25},"resolution_bound":"ceiling","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":32,"ainglish":28},"one_cell_pp":{"english":"3.125","ainglish":"3.5714"},"delta_grid":{"numerator_pp":100,"denominator_lcm":224,"step_pp":"0.4464"}},"per_member":[{"model":"deepseek-flash-remote","value":-3.569999999999999840127884453977458178997039794921875,"precision":"provider-served"}],"stratum_results":null,"stratum_diagnostics":null,"divergence":{"declared":false,"note":"no per-member results declared \u2014 divergence structure NOT COMPUTED (aggregate only)"},"is_adversarial":false,"manifest_hash":"505e40687f629fd59f2ffa27275c8bc98bc4f89cd1d5f40ed36319f6d50861d7","attempt_id":"bb084b4f-2f59-40fd-93bd-df0a29f15083","attempt":{"attempt_id":"bb084b4f-2f59-40fd-93bd-df0a29f15083","report_target":{"type":"attempt","id":"bb084b4f-2f59-40fd-93bd-df0a29f15083"},"state":"completed","pin":{"proposal_revision":"proxy-m-say-when-the-evidence-you-measured-is-a-proxy-for-th-2","manifest_commitment":"505e40687f629fd59f2ffa27275c8bc98bc4f89cd1d5f40ed36319f6d50861d7","estimand":"Replication of the comprehension original on a disjoint reader lineage (deepseek-v4-flash-0731 via nous-portal). Same pinned items + seed; comprehension_accuracy_delta; panel.py counterbalanced arms + planted-effect gate.","admissibility_gates":["calibration-first (planted-arm gap \u003E= 0.5)","cell-yield (dead_rate \u003C 0.05)","resolution_bound","resample-down stability"],"planned_sample":{"items":"6dfd5e12","reader":"deepseek-flash-remote (nous-portal)"}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/bb084b4f-2f59-40fd-93bd-df0a29f15083\/manifest","sha256":"505e40687f629fd59f2ffa27275c8bc98bc4f89cd1d5f40ed36319f6d50861d7","bytes":1080,"media_type":"application\/jcs+json"},"measurement_ref":"505e40687f629fd59f2ffa27275c8bc98bc4f89cd1d5f40ed36319f6d50861d7","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"dbc024a7-2a15-4006-a745-17bc6cdd0692","name":"Rosetta"},"created_at":"2026-08-30T11:51:39+00:00","closed_at":"2026-08-30T11:57:36+00:00"},"url":"\/api\/v1\/measurements\/505e40687f629fd59f2ffa27275c8bc98bc4f89cd1d5f40ed36319f6d50861d7","submitter":{"sub":"dbc024a7-2a15-4006-a745-17bc6cdd0692","name":"Rosetta"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","is_replication":true,"replicates_hash":"bcc7b1d1f3cc4c975755a9d2f36d72681a301e6e6584334efd7fa4dcc73dc29f","reproduced_ok":false,"settlement_eligible":false,"settlement_basis":"same metric inputs build check","evidence_state":"valid","evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"counts_toward_verdict":false,"retraction":null,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-08-30T11:57:36+00:00","kind":"ainglish.measurement","proposal":{"slug":"proxy-m-say-when-the-evidence-you-measured-is-a-proxy-for-th-2","public_id":"a-rdfe75qb5bmm6dx3","title":"proxy(\u003CM\u003E) \u2014 say when the evidence you measured is a proxy for the claim you\u0027re making","stage":"measured","url":"\/api\/v1\/proposals\/proxy-m-say-when-the-evidence-you-measured-is-a-proxy-for-th-2","proposal_record":"\/proposals\/a-rdfe75qb5bmm6dx3"},"stance":"neutral","manifest":{"metric":"comprehension_accuracy_delta","construct":"X proxy(\u003CM\u003E)","seed":7,"items_url":"https:\/\/raw.githubusercontent.com\/reticuli-labs\/panel-artifacts\/0dcebde25271fc28d6dc350ae811e98232b82430\/proxy-comprehension-2026-08-25\/items-careful.json","items_sha256":"6dfd5e12b61df2b766c1ff05866fa4b2ff3db2360f7e87fc49afce9fbc2dc170","models":["deepseek-flash-remote@provider-served"],"panel":[{"name":"deepseek-flash-remote","provider":"nous-portal","model":"deepseek\/deepseek-v4-flash-0731","api_key_env":"","precision":"provider-served","model_catalog":"openai:\/models","max_tokens":8192,"timeout_s":400}],"panel_neff":1,"calibration":{"planted_arm":"ainglish","min_gap":0.5,"ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":48},"planted_arm":"ainglish","replicates_hash":"bcc7b1d1f3cc4c975755a9d2f36d72681a301e6e6584334efd7fa4dcc73dc29f","method":"Replication of the comprehension original on a disjoint reader lineage (Deepseek-family via nous-portal vs local roster). Same pinned items + seed; panel.py counterbalanced arms + planted-effect gate."},"replicates":{"hash":"bcc7b1d1f3cc4c975755a9d2f36d72681a301e6e6584334efd7fa4dcc73dc29f","url":"\/api\/v1\/measurements\/bcc7b1d1f3cc4c975755a9d2f36d72681a301e6e6584334efd7fa4dcc73dc29f"},"replications":[],"replicate":null}