{"id":"W4386214112","doi":"10.1016/j.knosys.2023.110938","title":"Label correlation guided borderline oversampling for imbalanced multi-label data learning","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Weighting; Computer science; Machine learning; Class (philosophy); Multi-label classification; Artificial intelligence; Decision boundary; Range (aeronautics); Code (set theory); Correlation; Data mining; Source code; Tree (set theory); Macro; Pattern recognition (psychology); Support vector machine; 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":[],"consensus_categories":[],"category_scores_codex":[0.001177627,0.0002179135,0.0002910678,0.000353114,0.0003887416,0.0003367006,0.001652818,0.0001720419,0.000002836721],"category_scores_gemma":[0.0009891435,0.0002112644,0.00004606545,0.001209381,0.00004888095,0.0005680956,0.000410501,0.0001959948,0.0003472002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001235102,"about_ca_system_score_gemma":0.0001795182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002764539,"about_ca_topic_score_gemma":0.00001976056,"domain_scores_codex":[0.9979305,0.0001073966,0.000534556,0.0007544884,0.0002441866,0.0004288883],"domain_scores_gemma":[0.9972839,0.0006205363,0.0003124092,0.001393181,0.0003178579,0.0000720761],"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":[0.0001355693,0.001728155,0.03600642,0.002307085,0.000356624,0.00002104008,0.002966835,0.05966929,0.05232451,0.1839386,0.2117944,0.4487514],"study_design_scores_gemma":[0.002206,0.00007132708,0.0003822588,0.0001095475,0.00001117303,0.000001131586,0.0001836998,0.9578734,0.0004709268,0.0001423839,0.03830162,0.0002465256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002261329,0.0006398046,0.990483,0.000666327,0.001741,0.0007930902,0.00003596526,0.003099573,0.0002799526],"genre_scores_gemma":[0.8960868,0.00003622207,0.09402797,0.00004635313,0.0002400634,0.0004378772,0.001078723,0.00005766303,0.007988366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8982041,"threshold_uncertainty_score":0.8615112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1748491315610552,"score_gpt":0.3773169973589758,"score_spread":0.2024678657979206,"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."}}