{"id":"W2011376672","doi":"10.1145/1007730.1007737","title":"Class imbalances versus small disjuncts","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":681,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Focus (optics); Classifier (UML); Artificial intelligence; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002052662,0.0002469015,0.0001971132,0.0002012451,0.000272908,0.0004478452,0.002610336,0.0001151364,0.00002557672],"category_scores_gemma":[0.0003292368,0.0002341337,0.00008341561,0.0007420649,0.000113523,0.002011453,0.0005548025,0.0002468015,0.001054363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001650662,"about_ca_system_score_gemma":0.0001370464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110094,"about_ca_topic_score_gemma":0.00007739377,"domain_scores_codex":[0.9981174,0.00006877974,0.0003845946,0.0006315607,0.0003687071,0.000428922],"domain_scores_gemma":[0.9968916,0.0001860733,0.0001557384,0.002498135,0.0001435885,0.0001248217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007889464,0.0005443797,0.0008210528,0.00003678228,0.0001209024,0.00008160621,0.003674977,0.0008715389,0.0477502,0.6932518,0.2174866,0.03528124],"study_design_scores_gemma":[0.006100406,0.0007120852,0.00541481,0.0001284391,0.00006049424,0.00004207194,0.0004895467,0.002268243,0.2297273,0.1501286,0.6026062,0.002321754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008144988,0.00005157474,0.9044271,0.08279607,0.000939207,0.0003462788,0.00001435182,0.001199726,0.00208074],"genre_scores_gemma":[0.5063142,0.00007157026,0.4810038,0.01114897,0.0004498782,0.0004912788,0.0001699971,0.00003931447,0.0003109741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5431231,"threshold_uncertainty_score":0.9997234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.068174256664078,"score_gpt":0.279847161916715,"score_spread":0.211672905252637,"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."}}