{"id":"W1987916785","doi":"10.1016/j.jclinepi.2008.05.003","title":"Commentary on “Alternative graphs for diagnostic tests: the agreement chart and the receiver operating characteristic curve”","year":2008,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Receiver operating characteristic; Computer science; Chart; Perception; Feature (linguistics); Artificial intelligence; Information retrieval; Statistics; Psychology; Mathematics; Machine learning; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04025701,0.001508744,0.003646264,0.002494971,0.005635767,0.006425636,0.008357363,0.1143736,0.007344571],"category_scores_gemma":[0.2289878,0.002530482,0.003164899,0.002641029,0.009821454,0.007194918,0.003064139,0.09486851,0.006741627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008926266,"about_ca_system_score_gemma":0.007712069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01547074,"about_ca_topic_score_gemma":0.02292947,"domain_scores_codex":[0.957238,0.02181151,0.005286098,0.004542283,0.009129465,0.001992629],"domain_scores_gemma":[0.7740983,0.1859218,0.006425539,0.003583812,0.02524193,0.004728658],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007986269,0.00001482016,0.0002391414,0.00006777426,0.00002765759,0.000350748,0.0001828407,0.00006426101,0.00005993242,0.004222491,0.9909347,0.003755726],"study_design_scores_gemma":[0.0007625199,0.000150944,0.002462462,0.001739407,0.0002142697,0.001841226,0.000943159,0.002297702,0.0005960133,0.04388459,0.9447675,0.0003402465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0001456956,0.0003962633,0.0002882081,0.9853089,0.01314222,0.00001373785,0.00008680885,0.00003109324,0.0005869181],"genre_scores_gemma":[0.001155938,0.000152836,0.0005163142,0.9783343,0.01894203,0.00005141225,0.00002211641,0.00002241235,0.0008026655],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.959743,"threshold_uncertainty_score":0.2129019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.495071107522614,"score_gpt":0.520213486178791,"score_spread":0.02514237865617708,"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."}}