{"id":"W3007618168","doi":"10.48550/arxiv.2003.00316","title":"Model-based ROC (mROC) curve: examining the effect of case-mix and model calibration on the ROC plot","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Receiver operating characteristic; Calibration; Smoothing; Plot (graphics); Computer science; Sample (material); Statistics; Calibration curve; Context (archaeology); Sensitivity (control systems); Artificial intelligence; Mathematics; Engineering","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":[0.1041623,0.002344486,0.002593823,0.007509181,0.0008071916,0.005563051,0.00295068,0.003018707,0.007731509],"category_scores_gemma":[0.3787635,0.000787374,0.004579341,0.005610603,0.002527912,0.004062796,0.003786538,0.003046171,0.002703078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002096919,"about_ca_system_score_gemma":0.002485163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003599318,"about_ca_topic_score_gemma":0.001959881,"domain_scores_codex":[0.9328339,0.04435769,0.004040967,0.008374025,0.009357874,0.001035407],"domain_scores_gemma":[0.5391579,0.3732585,0.03225481,0.03198643,0.0214164,0.001925985],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004573437,0.0006082354,0.3204219,0.005343806,0.008293428,0.001236134,0.002854453,0.1653801,0.004505244,0.03763314,0.05310258,0.3960475],"study_design_scores_gemma":[0.0004836778,0.003028523,0.1754084,0.002325835,0.003156784,0.004486463,0.001746858,0.6659549,0.01144494,0.08023757,0.05088208,0.0008439193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1628128,0.009243466,0.7860016,0.003099243,0.0006965371,0.002073778,0.01307274,0.0108481,0.01215166],"genre_scores_gemma":[0.7611313,0.001485406,0.2228323,0.001079632,0.0002723312,0.002249254,0.006799793,0.002628476,0.001521648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8958377,"threshold_uncertainty_score":0.5508693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.358866620347382,"score_gpt":0.2718861623654973,"score_spread":0.0869804579818847,"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."}}