{"id":"W4298237571","doi":"10.48550/arxiv.1803.03877","title":"On dynamic ensemble selection and data preprocessing for multi-class\\n imbalance learning","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Preprocessor; Ensemble learning; Computer science; Artificial intelligence; Class (philosophy); Machine learning; Selection (genetic algorithm); Data pre-processing; Data mining; Binary number; Pattern recognition (psychology); 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"],"consensus_categories":[],"category_scores_codex":[0.001299419,0.0006977058,0.0006208635,0.0004850244,0.001145905,0.0006387787,0.004023858,0.0006243307,0.00001625268],"category_scores_gemma":[0.0006852992,0.000889957,0.0001194106,0.001002818,0.0003907552,0.0019556,0.004259564,0.001132339,0.00006865695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005955566,"about_ca_system_score_gemma":0.0004796666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005704637,"about_ca_topic_score_gemma":0.0001087559,"domain_scores_codex":[0.9935133,0.000342909,0.0005266885,0.004645929,0.0001873923,0.0007837984],"domain_scores_gemma":[0.9940742,0.0004267425,0.001143267,0.003411765,0.0006986852,0.0002453096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003905168,0.00460834,0.02864703,0.007671222,0.001855747,0.0002314916,0.004193778,0.4072028,0.0503618,0.3193803,0.008568003,0.1633743],"study_design_scores_gemma":[0.00100059,0.0003535499,0.001064238,0.000539906,0.000113199,0.00001484882,0.00006425394,0.9827157,0.001871889,0.009419021,0.001980274,0.0008625565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06352011,0.000072604,0.9335346,0.000085715,0.000465014,0.001151091,0.0001403654,0.0007088015,0.0003217298],"genre_scores_gemma":[0.9377538,0.0006784772,0.0579747,0.00009047833,0.00009467748,0.000009412873,0.0003831723,0.00006439381,0.00295089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8755599,"threshold_uncertainty_score":0.9993551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1478121485659862,"score_gpt":0.2722080545791093,"score_spread":0.1243959060131232,"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."}}