{"id":"W1516042217","doi":"10.1007/3-540-45153-6_1","title":"A Case Study for Learning from Imbalanced Data Sets","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Skew; Machine learning; Artificial intelligence; Rule induction; Quality (philosophy); Focus (optics); Data mining; Set (abstract data type); Variety (cybernetics); Training set","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":[],"consensus_categories":[],"category_scores_codex":[0.004838528,0.0005251144,0.0006059235,0.001103054,0.00136136,0.00219904,0.001703899,0.002893203,0.002184762],"category_scores_gemma":[0.02859184,0.0002514978,0.0006252751,0.002692774,0.001083144,0.002437978,0.001484905,0.001682224,0.0006099927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009089373,"about_ca_system_score_gemma":0.0006807788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003558503,"about_ca_topic_score_gemma":0.005760454,"domain_scores_codex":[0.9961939,0.00180681,0.0001729441,0.0004159965,0.001203891,0.0002064114],"domain_scores_gemma":[0.9766752,0.01865818,0.0005271779,0.001873483,0.001626632,0.0006393422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00206398,0.004393953,0.05866835,0.001478397,0.0003322421,0.01185443,0.005250194,0.1034437,0.008442413,0.05157114,0.06585097,0.6866502],"study_design_scores_gemma":[0.0006395907,0.00182278,0.02137818,0.0002763759,0.0001760331,0.012623,0.006812334,0.7459964,0.0213228,0.1137123,0.07510703,0.0001333318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6193374,0.003604394,0.3350136,0.01251131,0.0005259474,0.0008805055,0.002244678,0.001264392,0.02461772],"genre_scores_gemma":[0.7471854,0.0009999083,0.2399739,0.0006091475,0.0002344555,0.0002960371,0.001229093,0.0001608488,0.009311193],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004838528,"threshold_uncertainty_score":0.02558887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07340706613005715,"score_gpt":0.3196770846606314,"score_spread":0.2462700185305743,"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."}}