{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01571284,0.001955402,0.00177304,0.0009890302,0.001136059,0.00414056,0.002824498,0.003290057,0.002010527],"category_scores_gemma":[0.05903835,0.00081514,0.0008800573,0.002189785,0.001677036,0.00731201,0.003346402,0.004358598,0.0007441555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001997081,"about_ca_system_score_gemma":0.002875018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001640387,"about_ca_topic_score_gemma":0.002661429,"domain_scores_codex":[0.9912409,0.00392525,0.0006775917,0.002013434,0.001597886,0.0005450291],"domain_scores_gemma":[0.9660587,0.02144728,0.002599593,0.005739658,0.003041131,0.001113762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004415982,0.0006454972,0.01000688,0.0006500715,0.0002089012,0.000343297,0.0004093111,0.800877,0.005411304,0.05511559,0.01530514,0.1105854],"study_design_scores_gemma":[0.00005308184,0.0001817617,0.001854884,0.00007254832,0.00003274931,0.0001898082,0.0001815081,0.9184027,0.004134148,0.07056775,0.004294986,0.00003412658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0913453,0.0006708512,0.8949412,0.005282218,0.0001831445,0.0003818486,0.001335445,0.0007846203,0.005075307],"genre_scores_gemma":[0.5315704,0.0003914083,0.4596518,0.001805151,0.0002635305,0.001049114,0.002174913,0.0004054096,0.002688272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01571284,"threshold_uncertainty_score":0.08309847,"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."}}