{"id":"W1541033774","doi":"10.1007/978-3-642-13059-5_22","title":"Overlap versus Imbalance","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Classifier (UML); Interdependence; Training set; Isolation (microbiology); Artificial intelligence; Machine learning; Pattern recognition (psychology)","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":[0.003989602,0.001088802,0.001608358,0.002411784,0.001527661,0.004001568,0.00185776,0.001429617,0.01931017],"category_scores_gemma":[0.02321486,0.0006253642,0.0007187393,0.00361344,0.002395595,0.01093207,0.004873158,0.00260278,0.005769542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00102984,"about_ca_system_score_gemma":0.0007940763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004214318,"about_ca_topic_score_gemma":0.0004971123,"domain_scores_codex":[0.9947358,0.001471322,0.0002804399,0.001149135,0.001988999,0.0003743755],"domain_scores_gemma":[0.9892401,0.005918358,0.0004993114,0.00277828,0.001167546,0.0003964608],"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":[0.0003707466,0.00009109708,0.001758012,0.0002856544,0.0000539597,0.0001019567,0.0003913352,0.005504302,0.001909771,0.4939887,0.03963352,0.455911],"study_design_scores_gemma":[0.00002450143,0.0000883078,0.001047607,0.000108224,0.00004929551,0.000671678,0.0002585278,0.04703631,0.004369021,0.8642438,0.08207577,0.00002687711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0306743,0.008922033,0.8424236,0.005536315,0.00194689,0.0001881902,0.0009392523,0.001646961,0.1077224],"genre_scores_gemma":[0.5730159,0.007266629,0.2824387,0.002226221,0.006134871,0.0006759784,0.003132415,0.001772235,0.123337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01931017,"threshold_uncertainty_score":0.06459898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02038288687829102,"score_gpt":0.2655751414727915,"score_spread":0.2451922545945005,"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."}}