{"id":"W2963779314","doi":"","title":"Satisfying real-world goals with dataset constraints","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Machine learning; Classifier (UML); Real world data; Data mining; Artificial intelligence; Training set; Set (abstract data type); Precision and recall; Data science","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":[0.0003627354,0.0001558161,0.0001680606,0.0002383803,0.0001878587,0.0008020377,0.0006958469,0.0000469066,0.000008881848],"category_scores_gemma":[0.00004969992,0.00009566244,0.00001391082,0.0004529415,0.0001218554,0.01001219,0.00009591576,0.00008081862,0.0001154114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003115,"about_ca_system_score_gemma":0.0001218247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004615391,"about_ca_topic_score_gemma":0.000006941593,"domain_scores_codex":[0.9985244,0.00005517355,0.0005476813,0.0002106607,0.000406714,0.0002553384],"domain_scores_gemma":[0.9984782,0.00006819407,0.0005457851,0.0005983948,0.000227061,0.00008233493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002076201,0.00002218677,0.004045764,0.0004559448,0.00001647881,0.000006106784,0.0007226337,0.00007417647,0.003960692,0.07779823,0.03447925,0.8783978],"study_design_scores_gemma":[0.005507365,0.0005909478,0.02643886,0.005661537,0.00004651495,0.001094169,0.0008674861,0.3140905,0.0519212,0.001478539,0.5886478,0.003655024],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007911671,0.00001938239,0.9919694,0.0009584447,0.0001949639,0.0003909621,0.0004166131,0.0008964903,0.00436254],"genre_scores_gemma":[0.985028,0.00001065633,0.01394108,0.0004130705,0.00004144952,0.000095937,0.0002851987,0.000007943654,0.0001766456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9842368,"threshold_uncertainty_score":0.7734067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02706035043457996,"score_gpt":0.2794520838944358,"score_spread":0.2523917334598558,"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."}}