{"id":"W4411429323","doi":"10.21203/rs.3.rs-6895500/v1","title":"Introducing DART: A Novel Deep Adaptive Upsampling Technique for Handling Class Imbalance","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Undersampling; Resampling; Machine learning; Artificial intelligence; Oversampling; Computer science; Random forest; Multinomial logistic regression; Generalizability theory; Jackknife resampling; Data mining; Statistics; Mathematics; Bandwidth (computing)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001626321,0.001138469,0.001185936,0.001210824,0.0006286297,0.001547319,0.00195861,0.001290767,0.002860334],"category_scores_gemma":[0.004616783,0.0004762382,0.0008706137,0.001297847,0.000742936,0.002024967,0.002675392,0.00309479,0.001497247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006098746,"about_ca_system_score_gemma":0.001030163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002532443,"about_ca_topic_score_gemma":0.005167353,"domain_scores_codex":[0.9987617,0.000189722,0.0000637724,0.0002665996,0.0005930446,0.0001251515],"domain_scores_gemma":[0.9989647,0.0002858733,0.00008388707,0.0003210851,0.0002682515,0.0000762151],"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":[0.0002839866,0.0002153458,0.001772212,0.0001339585,0.0001245716,0.0001377179,0.0001650695,0.03927943,0.04629344,0.01301536,0.01032983,0.8882492],"study_design_scores_gemma":[0.00003157957,0.0000914814,0.000698317,0.00003059804,0.00004498818,0.0001831382,0.00005171988,0.9482401,0.02511228,0.01379872,0.01169308,0.0000240175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005810576,0.0002816793,0.9917371,0.0001726439,0.0001976712,0.00004708875,0.00008460799,0.001048741,0.0006198906],"genre_scores_gemma":[0.1520529,0.0005297084,0.8388754,0.0007047038,0.0004559357,0.000195994,0.0007525228,0.000327544,0.006105299],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002860334,"threshold_uncertainty_score":0.00956881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09381332995188661,"score_gpt":0.4068534410320782,"score_spread":0.3130401110801915,"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."}}