{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004215191,0.0003484662,0.0004702708,0.0001504951,0.0004151249,0.0001946895,0.0012983,0.0002118399,0.00004212905],"category_scores_gemma":[0.001227719,0.0002003275,0.0002268233,0.0005323882,0.0002866256,0.0001830603,0.0007509814,0.0006692523,0.00001622162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001054612,"about_ca_system_score_gemma":0.0001821005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006566005,"about_ca_topic_score_gemma":0.00007643332,"domain_scores_codex":[0.9963372,0.001190582,0.0004774825,0.001091365,0.0006628736,0.000240442],"domain_scores_gemma":[0.9946722,0.003164301,0.0005105396,0.001335038,0.0001948435,0.0001230772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002135485,0.00003557383,0.003878248,0.00005254122,0.00004602445,0.00004667154,0.0003426124,0.9900405,0.0001558008,0.004273689,0.0005788322,0.0003359445],"study_design_scores_gemma":[0.0004302002,0.0002563597,0.0002059672,0.00008758046,0.0001356248,0.000001736705,0.0003051795,0.9689771,0.0009763206,0.02839399,0.00002651579,0.0002034058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7602907,0.00003467986,0.2373574,0.0007555828,0.0001123477,0.0007062683,0.00003948723,0.0000350848,0.0006684889],"genre_scores_gemma":[0.9992659,0.00002443055,0.0001055638,0.0002790601,0.00003694145,0.000005108368,0.000006577923,0.00001561997,0.0002608063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2389752,"threshold_uncertainty_score":0.8169118,"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."}}