{"id":"W752888290","doi":"10.1007/s10844-015-0368-1","title":"Types of minority class examples and their influence on learning classifiers from imbalanced data","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":287,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Ottawa","keywords":"Computer science; Outlier; Machine learning; Artificial intelligence; Identification (biology); Class (philosophy); Classifier (UML); Neighbourhood (mathematics); Data mining; Data type; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001351233,0.0001291436,0.0002995665,0.0002598105,0.00004487832,0.0002301155,0.001255998,0.00008366749,0.000001302124],"category_scores_gemma":[0.0006941609,0.00009461749,0.00003215619,0.0002278364,0.00005922015,0.003588855,0.0002339597,0.0002581027,0.00001696548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009659,"about_ca_system_score_gemma":0.0001547429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009760422,"about_ca_topic_score_gemma":0.00000171681,"domain_scores_codex":[0.9981136,0.0001425164,0.00103537,0.0001235224,0.0004604348,0.0001245828],"domain_scores_gemma":[0.9966052,0.0002604786,0.00156875,0.0006564761,0.0007864097,0.0001227136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009484206,0.0005076478,0.0608161,0.000979377,0.0009387216,0.00001553881,0.05630567,0.05740239,0.01703307,0.2590288,0.06235243,0.4836718],"study_design_scores_gemma":[0.001272526,0.001233669,0.01091954,0.00127429,0.00003453498,0.0001692794,0.01319884,0.417071,0.04823048,0.001887337,0.5040334,0.0006750891],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07507265,0.0004770244,0.9212421,0.0001960548,0.0006396295,0.0002208979,0.00009033801,0.00007705297,0.001984222],"genre_scores_gemma":[0.9931608,0.0002162975,0.006401529,0.00008771746,0.00006216612,0.00000274592,0.00004832526,0.0000030457,0.00001732794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9180882,"threshold_uncertainty_score":0.3858389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07618345526224594,"score_gpt":0.2870352410138041,"score_spread":0.2108517857515581,"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."}}