{"id":"W3160953847","doi":"10.1007/s10994-021-06012-8","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Infrastruktura PL-Grid; Narodowe Centrum Nauki","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Artificial intelligence; Prior probability; Binary classification; Binary number; Pattern recognition (psychology); Class (philosophy); Data mining; Machine learning; Algorithm; Mathematics; Support vector machine; Bayesian probability","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001924782,0.0004655082,0.0006231827,0.0003058348,0.0005008031,0.001248621,0.002837503,0.0003679924,0.000008349968],"category_scores_gemma":[0.001076445,0.000526445,0.0001026423,0.0003620573,0.00009288242,0.0006231011,0.003417355,0.001298059,0.000003238293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00015239,"about_ca_system_score_gemma":0.000325844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078913,"about_ca_topic_score_gemma":0.00001749932,"domain_scores_codex":[0.9959598,0.0004015044,0.0007119604,0.002002802,0.0004309624,0.0004930022],"domain_scores_gemma":[0.9949072,0.0006859974,0.0008147274,0.003169101,0.0002780066,0.0001449911],"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":[0.0000395575,0.0001510266,0.003696268,0.0005159887,0.0001202094,0.00001576145,0.0005377568,0.003107612,0.005744027,0.005488285,0.001245106,0.9793384],"study_design_scores_gemma":[0.0007708485,0.00007567042,0.002388939,0.0002684832,0.00003570364,0.000006181052,0.00004929564,0.9829503,0.001098513,0.0007696512,0.01104564,0.0005407525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006767655,0.0005301067,0.99401,0.001744479,0.0005365028,0.0008405674,0.000248834,0.001275235,0.0001375394],"genre_scores_gemma":[0.1217251,0.0001628997,0.863597,0.0003294038,0.0002175754,0.0002354989,0.01353756,0.00007757984,0.0001173854],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9798427,"threshold_uncertainty_score":0.9997882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06623426337024325,"score_gpt":0.321198295922057,"score_spread":0.2549640325518138,"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."}}