{"id":"W4401399881","doi":"10.1142/9789811267048_0026","title":"On Removing Diverse Data for Training Machine Learning Models","year":2024,"lang":"en","type":"book-chapter","venue":"Series on computers and operations research","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Concordia University; Group for Research in Decision Analysis","funders":"","keywords":"Training (meteorology); Computer science; Machine learning; Artificial intelligence; Training set; Geography","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001320679,0.0003193577,0.0003345241,0.0005604357,0.001398841,0.001568279,0.001381833,0.0001644427,0.00002436283],"category_scores_gemma":[0.0001150569,0.0002805775,0.00007608131,0.0001280123,0.0001499006,0.0005884368,0.001747196,0.0016556,0.00005654667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006368737,"about_ca_system_score_gemma":0.000177309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008506001,"about_ca_topic_score_gemma":0.00009612431,"domain_scores_codex":[0.9973559,0.00009872297,0.0002787959,0.001191311,0.0006416675,0.0004335472],"domain_scores_gemma":[0.997936,0.0006077034,0.00003237836,0.001065793,0.0001986444,0.0001595062],"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":[0.00001593668,0.00001083677,1.295224e-7,0.00005646448,0.00005144313,0.00004120416,0.0009380567,0.08756448,0.00000221199,0.7704124,0.002314741,0.1385921],"study_design_scores_gemma":[0.0001808925,0.0006544528,2.976882e-7,0.0004182294,0.000007639667,0.0000194982,0.00005675754,0.8558839,0.000001428081,0.02209793,0.1204228,0.0002561428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00008228784,0.001566937,0.8304228,0.008530332,0.001673135,0.001280488,0.0005044677,0.0005943979,0.1553452],"genre_scores_gemma":[0.007822576,0.001229176,0.1193545,0.0005182116,0.001238592,0.0000569362,0.001236995,0.0001660969,0.8683769],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7683194,"threshold_uncertainty_score":0.9999647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2136281158318142,"score_gpt":0.3666885289686321,"score_spread":0.1530604131368179,"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."}}