{"id":"W2972580158","doi":"10.1002/int.22120","title":"Synthetic minority oversampling for function approximation problems","year":2019,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Categorical variable; Computer science; Artificial intelligence; Machine learning; Function approximation; Preprocessor; Benchmark (surveying); Function (biology); Data mining; Mathematics; Algorithm; Artificial neural network","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":[0.0009651469,0.0001127892,0.0001900521,0.0003105469,0.00003187065,0.0002851987,0.001129527,0.0000669978,0.00001334824],"category_scores_gemma":[0.0001520007,0.00009840781,0.0001323316,0.000115876,0.00001505002,0.0009170065,0.00007020243,0.0001244628,0.00005312799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002676404,"about_ca_system_score_gemma":0.00007169138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001452716,"about_ca_topic_score_gemma":5.564505e-7,"domain_scores_codex":[0.9982414,0.00005213837,0.0007381464,0.0002116129,0.0006214133,0.0001353075],"domain_scores_gemma":[0.9973214,0.000186363,0.0008842282,0.0003019397,0.001254549,0.0000515823],"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":[0.0002546028,0.0004704937,0.004379003,0.0004139423,0.0006090858,0.000006639592,0.0009469682,0.01534924,0.05842667,0.849571,0.006617675,0.06295463],"study_design_scores_gemma":[0.001461998,0.001085693,0.001319814,0.001307391,0.00005997389,0.0006216957,0.0005282423,0.6593852,0.0662035,0.02425353,0.2430815,0.0006914231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003937944,0.0001785859,0.9890811,0.0003571709,0.005241145,0.0004781902,0.00001185615,0.00006210843,0.0006518819],"genre_scores_gemma":[0.976511,0.00004417958,0.02259063,0.00007280464,0.0003740405,0.00003379635,0.00001618175,0.000009475591,0.000347873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972573,"threshold_uncertainty_score":0.4012954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03005787058750423,"score_gpt":0.2787268652002383,"score_spread":0.248668994612734,"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."}}