{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1434863,0.0004615746,0.003771098,0.0001762176,0.0005847135,0.0001048277,0.002232592,0.0006052018,0.0001836784],"category_scores_gemma":[0.4779587,0.0001811853,0.001608895,0.0001770463,0.002193715,0.0001448004,0.0002708267,0.004800979,0.00004684435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008541581,"about_ca_system_score_gemma":0.0001430788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005451799,"about_ca_topic_score_gemma":0.00001277346,"domain_scores_codex":[0.9590475,0.02757781,0.01004578,0.0008494858,0.001843173,0.0006362525],"domain_scores_gemma":[0.4445132,0.5450944,0.008301892,0.0009150272,0.001015584,0.0001598896],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000401641,0.0001288394,0.03011086,0.00001973832,0.0003542266,0.00005549714,0.0001973853,0.000108894,3.066156e-7,0.0003494783,0.9573628,0.01091031],"study_design_scores_gemma":[0.002905281,0.001910834,0.05329249,0.0003751136,0.0002093101,0.00007202749,0.0001062529,0.0007369848,7.509389e-7,0.08815455,0.8520125,0.0002238965],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.01384038,0.001147361,0.00176267,0.9758306,0.00584533,0.001313037,0.00008089995,0.000004370229,0.0001753403],"genre_scores_gemma":[0.01143819,0.009475777,0.0006745548,0.9665728,0.01138232,0.00009098307,0.00001934151,0.00002053561,0.0003254642],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.5175166,"threshold_uncertainty_score":0.997495,"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."}}