{"id":"W151594930","doi":"10.1007/978-3-642-30217-6_19","title":"Foundation of Mining Class-Imbalanced Data","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Class (philosophy); Bounded function; Upper and lower bounds; Machine learning; Artificial intelligence; Data mining; Order (exchange); Word error rate; Sample complexity; Empirical research; Sample (material); Statistics; Mathematics","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001541108,0.0004152752,0.0005343347,0.0007749571,0.0001391648,0.0002893063,0.008414654,0.0003001291,0.00003006548],"category_scores_gemma":[0.0002401916,0.0004056926,0.00006129062,0.0006511619,0.0007086357,0.002169463,0.00357589,0.0005083051,0.00004447047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002664575,"about_ca_system_score_gemma":0.000622479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001153091,"about_ca_topic_score_gemma":0.00002694339,"domain_scores_codex":[0.9960964,0.00004123526,0.0007427422,0.001523303,0.001031785,0.0005645234],"domain_scores_gemma":[0.9935108,0.0004716179,0.0007456632,0.00483078,0.0003140381,0.0001270891],"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":[0.000003447886,0.000029642,0.0001410796,0.00004662301,0.000008934023,0.000004844871,0.0003277253,0.0003025763,0.00121557,0.04344382,0.0001348453,0.9543409],"study_design_scores_gemma":[0.0004971052,0.0002190154,0.001270183,0.0009614759,0.00002843671,0.00008078309,5.467727e-7,0.8519245,0.01969038,0.09605468,0.02772472,0.001548121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002827584,0.0003165622,0.9938824,0.0004632244,0.0010598,0.0003416431,0.00003169779,0.0002581009,0.003618361],"genre_scores_gemma":[0.1282822,0.0001001294,0.8704468,0.0004755443,0.0003375996,0.000008801089,0.0001476382,0.00003217415,0.0001691059],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9527928,"threshold_uncertainty_score":0.9998395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05203166455733296,"score_gpt":0.2970614443172095,"score_spread":0.2450297797598765,"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."}}