{"id":"W2094794062","doi":"10.6000/1929-6029.2012.01.01.08","title":"Performance Measures in Binary Classification","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Predictive value; Receiver operating characteristic; Binary classification; Statistics; Sensitivity (control systems); Mathematics; Binary number; Value (mathematics); Likelihood ratios in diagnostic testing; Artificial intelligence; Pattern recognition (psychology); Computer science; Medicine; Support vector machine; Internal medicine; Engineering; Arithmetic","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00944539,0.0000695578,0.0001378066,0.001052061,0.00003035818,0.00007280858,0.002243611,0.00009469407,0.00007922769],"category_scores_gemma":[0.005948351,0.00006114464,0.00001915281,0.0005554495,0.0001734488,0.0008590941,0.0002667173,0.0009859571,0.00003276426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004602152,"about_ca_system_score_gemma":0.0004956839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002275405,"about_ca_topic_score_gemma":0.00001273976,"domain_scores_codex":[0.9947486,0.0003840816,0.0006937137,0.0001336657,0.003703459,0.0003364803],"domain_scores_gemma":[0.9972546,0.001041424,0.0001789321,0.0002230002,0.001106788,0.0001953116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006303041,0.0005189126,0.09317636,0.00001625199,0.0000142619,0.0001858231,0.0006214233,0.00001367814,0.001175893,0.1917216,0.00822936,0.7042634],"study_design_scores_gemma":[0.001096613,0.0002222471,0.8313088,0.0005111743,0.000001527733,0.0002292366,0.0001880356,0.1192642,0.0017505,0.01421299,0.03102669,0.0001879704],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04919063,0.0002480576,0.9409952,0.005993308,0.001075934,0.0001269817,0.00001569633,0.00001894367,0.002335315],"genre_scores_gemma":[0.9311994,0.001408365,0.06701578,0.0001140761,0.0002064643,0.00001102526,0.000006890494,0.000005644508,0.00003238114],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8820087,"threshold_uncertainty_score":0.7121161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1422136878599545,"score_gpt":0.4601962357699261,"score_spread":0.3179825479099716,"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."}}