{"id":"W3202032933","doi":"10.1007/s00362-021-01266-9","title":"Asymptotic analysis of reliability measures for an imperfect dichotomous test","year":2021,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reliability (semiconductor); Statistics; Consistency (knowledge bases); Mathematics; Convergence (economics); Test (biology); Econometrics; Imperfect; Gold standard (test); Aggregate (composite); Economics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003490192,0.0001363697,0.000416669,0.00006195709,0.0001172323,0.00002820293,0.000111299,0.00007120766,0.0011137],"category_scores_gemma":[0.0192471,0.000125327,0.000150102,0.0006379134,0.0002102818,0.00003988163,0.00001986239,0.00008747516,0.000009696211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006078676,"about_ca_system_score_gemma":0.0001076387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001688029,"about_ca_topic_score_gemma":0.00009020361,"domain_scores_codex":[0.9984999,0.0001083551,0.0005025693,0.0003589057,0.0003051592,0.0002251166],"domain_scores_gemma":[0.992017,0.006776154,0.0001036297,0.0004320804,0.0004668839,0.0002042428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002203464,0.0006273945,0.0009675042,0.000104475,0.0002278617,0.000001971199,0.00006502263,0.00009119457,0.00400764,0.9880314,0.001244301,0.004609213],"study_design_scores_gemma":[0.001434145,0.000522351,0.2200301,0.00003332995,0.006159474,0.000006728035,0.000473855,0.1176068,0.003306009,0.6469452,0.002803276,0.0006787199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01095421,0.000009428995,0.975883,0.0001914718,0.00003287846,0.0003305622,0.007771877,0.00007591542,0.004750623],"genre_scores_gemma":[0.909029,0.000003310521,0.08963887,0.00008706949,0.00001468793,0.0001022238,0.0009838825,0.0000140119,0.0001269518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8980748,"threshold_uncertainty_score":0.9997994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05453612032085108,"score_gpt":0.3835623732133685,"score_spread":0.3290262528925174,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}