{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01772589,0.002216163,0.002144507,0.001253226,0.001405206,0.004572876,0.003388324,0.004145375,0.002181918],"category_scores_gemma":[0.06520027,0.0009441692,0.001047964,0.002756276,0.002027887,0.008012199,0.003900417,0.00558181,0.0009370169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002284865,"about_ca_system_score_gemma":0.003050966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001613227,"about_ca_topic_score_gemma":0.002625657,"domain_scores_codex":[0.9895342,0.004558588,0.0007512752,0.002662535,0.001887894,0.0006055254],"domain_scores_gemma":[0.9613611,0.02435691,0.002938173,0.007001441,0.003083579,0.001258766],"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":[0.0005314602,0.0008104307,0.01390929,0.0007739698,0.0002442719,0.000418534,0.0005632316,0.7452857,0.005690733,0.07468919,0.02191341,0.1351698],"study_design_scores_gemma":[0.00005911299,0.0001642134,0.001940869,0.00007905644,0.00003464517,0.0002241823,0.0002044804,0.8928368,0.003618182,0.09587106,0.004932577,0.000034812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07348952,0.0006858164,0.9127544,0.005836175,0.0001972497,0.0003609338,0.001308036,0.0008545764,0.004513377],"genre_scores_gemma":[0.4989812,0.0004313401,0.4909529,0.002158948,0.0003727145,0.00111496,0.002392987,0.0004877592,0.003107228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01772589,"threshold_uncertainty_score":0.09374464,"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."}}