{"id":"W4414706630","doi":"10.1016/j.icte.2025.09.011","title":"Imbalanced classification with label noise: A systematic review and comparative analysis","year":2025,"lang":"en","type":"article","venue":"ICT Express","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus","funders":"Directorate for Computer and Information Science and Engineering; Directorate for STEM Education; National Science Foundation","keywords":"Resampling; Class (philosophy); Identification (biology); Noise (video); Empirical research; Ensemble learning; Domain (mathematical analysis); Multi-label classification","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":[0.0003043861,0.000160784,0.0006461251,0.0002283701,0.00009979993,0.0001612596,0.0007851808,0.00004456814,0.000003042556],"category_scores_gemma":[0.00005418594,0.0001212886,0.00003896468,0.001643581,0.00007110467,0.0004496094,0.0001349257,0.00009984546,0.000009022851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005031822,"about_ca_system_score_gemma":0.00004292254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000875223,"about_ca_topic_score_gemma":0.000005265591,"domain_scores_codex":[0.9986223,0.0001793267,0.0003784771,0.0004527748,0.0002077615,0.0001593833],"domain_scores_gemma":[0.9980606,0.0001402759,0.0002755352,0.001263647,0.0002103646,0.00004960006],"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":[0.00003775438,0.0005128661,0.003703915,0.1697081,0.002816793,0.00000952532,0.00190836,0.00002593521,0.02278517,0.7812716,0.01623414,0.0009858451],"study_design_scores_gemma":[0.005875794,0.0007330478,0.136594,0.2207191,0.02422797,0.00007342867,0.001352109,0.518591,0.06905949,0.006762326,0.01087947,0.005132254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003663485,0.006696311,0.9862686,0.001335003,0.00002407902,0.001257744,0.00002133132,0.0003917714,0.003638856],"genre_scores_gemma":[0.9116329,0.001289169,0.08269082,0.001730302,0.000007294682,0.001270068,0.0000611613,0.000006473819,0.00131181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9112666,"threshold_uncertainty_score":0.4946007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03347594150859454,"score_gpt":0.313325711634043,"score_spread":0.2798497701254484,"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."}}