{"id":"W3184302936","doi":"","title":"Identifying Regions of Trusted Predictions","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science; Pointwise; Machine learning; Artificial intelligence; Process (computing); Domain (mathematical analysis); Data mining; Confidence interval; Sample complexity; Sample (material); Statistics; Mathematics","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":[0.01279355,0.001090809,0.001905015,0.002139059,0.001538817,0.005358974,0.003552448,0.002890103,0.003989433],"category_scores_gemma":[0.123256,0.001233248,0.001620713,0.001525692,0.0044438,0.007848712,0.007319223,0.003681789,0.001088714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002084403,"about_ca_system_score_gemma":0.002311049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002629122,"about_ca_topic_score_gemma":0.001651844,"domain_scores_codex":[0.990298,0.002624153,0.0005413129,0.002222119,0.003441052,0.0008735273],"domain_scores_gemma":[0.8608825,0.1047,0.01027596,0.0132707,0.009048479,0.001822308],"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":[0.001830271,0.0001746472,0.03449829,0.000674856,0.0002085506,0.001242734,0.002733451,0.4785439,0.01420157,0.3409552,0.006424603,0.118512],"study_design_scores_gemma":[0.00005055386,0.0001278672,0.002665058,0.0001233579,0.00004492971,0.0003723094,0.0002623736,0.7213654,0.01574913,0.2562139,0.002967632,0.00005760787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08944411,0.0006533541,0.9039595,0.0009463128,0.00003906128,0.00009026998,0.0005708079,0.001060808,0.003235813],"genre_scores_gemma":[0.8567128,0.0003534605,0.1394808,0.0003330635,0.0001209564,0.0002146455,0.001261294,0.0004577344,0.001065181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01279355,"threshold_uncertainty_score":0.06765962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05836014756836001,"score_gpt":0.3227540973834027,"score_spread":0.2643939498150427,"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."}}