{"id":"W3164230923","doi":"10.1145/3441250.3441274","title":"Threshold Moving Approaches for Addressing the Class Imbalance Problem and their Application to Multi-label Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multi-label classification; Class (philosophy); Computer science; Relevance (law); Artificial intelligence; Binary classification; Training set; Binary number; Machine learning; Simple (philosophy); Pattern recognition (psychology); Data mining; Mathematics; Support vector machine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004330918,0.0001921865,0.0001702836,0.00005136807,0.0003097933,0.000373456,0.001172466,0.00008164007,7.06009e-7],"category_scores_gemma":[0.00008243734,0.0001297519,0.00003212679,0.0004647976,0.00007344753,0.0005972458,0.0003214551,0.0001456094,0.00001054799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004623609,"about_ca_system_score_gemma":0.00004406391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004568035,"about_ca_topic_score_gemma":0.000006189724,"domain_scores_codex":[0.9984851,0.00004474207,0.0003151707,0.0007299698,0.0001565982,0.0002684247],"domain_scores_gemma":[0.9986672,0.0001423649,0.0001792217,0.0007715874,0.0001143279,0.0001252481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001866414,0.00009156236,0.0005897337,0.00009434894,0.00001676444,9.386724e-8,0.002441462,0.00008419991,0.138659,0.4934288,0.004306013,0.3602694],"study_design_scores_gemma":[0.0002434165,0.00004615719,0.001447124,0.00001545401,0.00000350735,0.000001832972,0.0002782667,0.9742014,0.0156385,0.002718044,0.005216612,0.0001896762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005490381,0.00008225611,0.9638638,0.03235014,0.00002342704,0.001721527,0.00001806188,0.0006204643,0.0007712874],"genre_scores_gemma":[0.5777394,0.00001010928,0.418692,0.00245451,0.0000531783,0.0009654299,0.00002266016,0.00001532652,0.00004738723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9741172,"threshold_uncertainty_score":0.5291128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2065772010912053,"score_gpt":0.3141587319339968,"score_spread":0.1075815308427915,"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."}}