{"id":"W1518941025","doi":"10.1002/9781118445112.stat05240","title":"Gold Standard Test","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Quality and Safety in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Test (biology); Ideal (ethics); Gold standard (test); Computer science; Statistics; Mathematics; Epistemology; Geology; Philosophy","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":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.001003233,0.0008809692,0.001628758,0.000409788,0.0005064407,0.00002885461,0.0007851266,0.001646694,0.02264984],"category_scores_gemma":[0.001924284,0.0007997864,0.00009182791,0.0003396129,0.0003570032,0.00005074583,0.0003034369,0.003441212,0.004729812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00048281,"about_ca_system_score_gemma":0.001994806,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003060561,"about_ca_topic_score_gemma":0.02536562,"domain_scores_codex":[0.9931208,0.00129598,0.001839959,0.001047222,0.001151713,0.001544343],"domain_scores_gemma":[0.9921099,0.003509229,0.001517998,0.001464894,0.0006921933,0.0007058138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008394883,0.0001496064,0.001453756,0.003209857,0.00006884678,0.00003574833,0.0003656431,0.000001246391,0.000002818788,0.05078729,0.9228523,0.02098892],"study_design_scores_gemma":[0.001067635,0.0004901246,0.000534916,0.003941998,0.00009987785,0.000002156425,0.0006935625,0.0001295365,3.752988e-7,0.008892565,0.9833101,0.0008371436],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001972144,0.001966454,0.06358819,0.002169033,0.002862254,0.002668459,0.4519911,0.001318488,0.4734162],"genre_scores_gemma":[0.0002077812,0.01045123,0.1094726,0.003493472,0.002637999,0.0001922345,0.02883347,0.001248874,0.8434623],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4231577,"threshold_uncertainty_score":0.9996494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1201307247938366,"score_gpt":0.4665647489039973,"score_spread":0.3464340241101607,"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."}}