{"id":"W4287183744","doi":"10.48550/arxiv.2105.04009","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for\\n imbalanced data classification","year":2021,"lang":"en","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":"National Research Council Canada","funders":"","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Binary classification; Artificial intelligence; Binary number; Prior probability; Class (philosophy); Data mining; Machine learning; Pattern recognition (psychology); 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"],"consensus_categories":[],"category_scores_codex":[0.00076595,0.000371637,0.0004577396,0.0003073331,0.0003073059,0.0005056702,0.003502462,0.0003756458,0.000004827635],"category_scores_gemma":[0.0002013218,0.000480181,0.0001052607,0.0006087742,0.0001626683,0.0009690059,0.002933715,0.0005425593,0.000004644862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002469575,"about_ca_system_score_gemma":0.0004443888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005927201,"about_ca_topic_score_gemma":0.0000175523,"domain_scores_codex":[0.9966407,0.0001995834,0.0003767577,0.002231848,0.0001437673,0.0004073439],"domain_scores_gemma":[0.9943293,0.0003962552,0.0005458129,0.004205588,0.0003519481,0.0001710354],"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":[0.0002900628,0.001086283,0.008057262,0.001312936,0.0007124356,0.0003673199,0.000868837,0.02388442,0.007814935,0.6361327,0.009348078,0.3101247],"study_design_scores_gemma":[0.0008451947,0.00004767708,0.001928643,0.0001604777,0.00005990601,0.000002487996,0.00009273364,0.9875354,0.0009696552,0.006569972,0.00128,0.0005078284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00463503,0.00006991449,0.9926188,0.000325242,0.0004546556,0.0006975093,0.0003002493,0.000721126,0.0001774767],"genre_scores_gemma":[0.6293393,0.0002149565,0.3673206,0.0001733591,0.00008383174,0.000009834324,0.002703634,0.0000331161,0.0001213888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.963651,"threshold_uncertainty_score":0.999765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1662660800452708,"score_gpt":0.2443103710650201,"score_spread":0.07804429101974933,"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."}}