{"id":"W2170505850","doi":"10.1016/j.ipm.2009.03.002","title":"A systematic analysis of performance measures for classification tasks","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6477,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Children's Hospital of Eastern Ontario","funders":"McGill University","keywords":"Confusion matrix; Confusion; Computer science; Artificial intelligence; Classifier (UML); Measure (data warehouse); Binary classification; Machine learning; Binary number; Natural language processing; Set (abstract data type); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics; Support vector machine; Arithmetic","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04296086,0.002308063,0.003285629,0.01642598,0.001276854,0.004170145,0.002322449,0.001661381,0.001398087],"category_scores_gemma":[0.2121844,0.0006902757,0.003032821,0.0144615,0.001154326,0.006485946,0.00166588,0.001895476,0.0008811959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002928945,"about_ca_system_score_gemma":0.005282739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0021972,"about_ca_topic_score_gemma":0.002573391,"domain_scores_codex":[0.9434702,0.02278243,0.009944817,0.005848186,0.01706079,0.0008935057],"domain_scores_gemma":[0.6392259,0.2589121,0.02155054,0.02473727,0.05435722,0.001216923],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.001123516,0.0007143526,0.03851762,0.008708969,0.002275045,0.00006682261,0.0004466531,0.007389662,0.007306534,0.004905843,0.005894669,0.9226502],"study_design_scores_gemma":[0.001210351,0.02324227,0.436339,0.01538329,0.02125275,0.003564087,0.003585388,0.2321429,0.111346,0.0676584,0.08259093,0.001684579],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1847833,0.1278953,0.6584609,0.001885534,0.0007137501,0.003107831,0.0102155,0.003477837,0.00946],"genre_scores_gemma":[0.5946142,0.02094457,0.3656338,0.0005874314,0.00052824,0.003279579,0.01132626,0.0008729079,0.002212978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9570391,"threshold_uncertainty_score":0.2272014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02272805573408605,"score_gpt":0.2683619694755179,"score_spread":0.2456339137414319,"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."}}