{"id":"W2169074127","doi":"10.1109/icsmc.1998.727521","title":"Using misclassified training samples to improve classification","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Classifier (UML); Computer science; Training set; Artificial intelligence; Pattern recognition (psychology); Machine learning; Test set; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0002586055,0.0001589147,0.0001613742,0.0002102915,0.0001590283,0.0002615342,0.001054672,0.00008171568,0.0001149783],"category_scores_gemma":[0.0001429873,0.0001520394,0.00004720675,0.0006104861,0.00003700556,0.0007371724,0.0001683874,0.0001137091,0.0002118287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195662,"about_ca_system_score_gemma":0.00003113886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001747939,"about_ca_topic_score_gemma":0.000004205482,"domain_scores_codex":[0.9983906,0.00005347705,0.0003320927,0.0005950721,0.0002812109,0.0003476196],"domain_scores_gemma":[0.9984418,0.00008072444,0.0001174026,0.001095744,0.0001083688,0.000155986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001610839,0.00005392262,0.00009470579,0.000006506994,0.000007991301,0.000001536505,0.001016837,0.0000111071,0.4805838,0.2816641,0.008182579,0.2283753],"study_design_scores_gemma":[0.000321581,0.0001003659,0.0041949,0.00003093802,0.000008186731,0.00002208332,0.0003532424,0.8144016,0.1151058,0.004720265,0.06008126,0.0006598738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001656951,0.00001363953,0.9773179,0.002853575,0.0001998789,0.0002852245,0.00001306787,0.0009523213,0.01670744],"genre_scores_gemma":[0.4491866,0.000004665214,0.5491012,0.00083315,0.00005365932,0.00003895105,0.000005342192,0.00001124659,0.0007651796],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8143904,"threshold_uncertainty_score":0.6199988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2821125264670423,"score_gpt":0.3297281373931616,"score_spread":0.04761561092611938,"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."}}