{"id":"W2473695717","doi":"10.48550/arxiv.1606.07558","title":"Satisfying Real-world Goals with Dataset Constraints","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Real world data; Classifier (UML); Machine learning; Set (abstract data type); Training set; Data mining; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003139722,0.0003546569,0.0003584028,0.0003996334,0.0001504302,0.0001833322,0.002963998,0.0001869665,0.0000894831],"category_scores_gemma":[0.00002924514,0.000322939,0.00006889068,0.0005378716,0.0004215691,0.0007898626,0.002206897,0.0004349783,0.0001743654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101067,"about_ca_system_score_gemma":0.0003470775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001494656,"about_ca_topic_score_gemma":0.0001416245,"domain_scores_codex":[0.9976174,0.0001557334,0.000248954,0.001430793,0.0001427847,0.0004043446],"domain_scores_gemma":[0.9960371,0.0001632834,0.0004566447,0.00300655,0.0001549063,0.0001815006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002938858,0.00006481112,0.009007031,0.00008337478,0.0001148107,0.0004457074,0.00005806876,0.0003999686,0.0003265562,0.9665933,0.01767862,0.005198325],"study_design_scores_gemma":[0.00639653,0.0005410234,0.05359517,0.004622585,0.0005214132,0.0001387291,0.0002040065,0.1291391,0.02477965,0.6747217,0.09587377,0.009466373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002290467,0.000008279808,0.9821938,0.0002617225,0.0001843174,0.000411711,0.002611024,0.0007589016,0.01127976],"genre_scores_gemma":[0.9738288,0.000209062,0.02358109,0.0001821784,0.00005304672,0.000004109997,0.0007944846,0.00002454052,0.001322708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9715383,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09058333476013208,"score_gpt":0.224372604028407,"score_spread":0.1337892692682749,"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."}}