{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003641082,0.0001132334,0.0001898349,0.0001889811,0.0001184846,0.00009219883,0.0005433441,0.00006537115,0.00008682872],"category_scores_gemma":[0.0004752712,0.0001175435,0.00009032487,0.001377708,0.00009107994,0.0002027405,0.000180343,0.0002879927,0.00004360639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004831524,"about_ca_system_score_gemma":0.0001508625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004715599,"about_ca_topic_score_gemma":0.0003613447,"domain_scores_codex":[0.9984262,0.0001566932,0.0005060093,0.0003828249,0.0002635497,0.0002647261],"domain_scores_gemma":[0.9988704,0.0002290607,0.0001153762,0.0005249449,0.0001895445,0.00007072114],"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":[0.00000759517,0.0002442059,0.0004393905,0.00002607337,0.00001636315,0.00007868848,0.003136202,0.1341852,0.003117717,0.7210572,0.0001110775,0.1375802],"study_design_scores_gemma":[0.00003355698,0.00004140624,0.0004182564,0.0001089619,0.00000546745,0.00002682111,0.0009631577,0.8492627,0.02537849,0.1229124,0.0006844457,0.0001642941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01170376,0.0001430631,0.9837835,0.001505859,0.0007080999,0.00008521359,0.000004152583,0.0001157772,0.001950597],"genre_scores_gemma":[0.9789599,0.00004367085,0.02048241,0.00008854523,0.00007752008,0.00001162089,0.000006658059,0.000006601255,0.0003231109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9672561,"threshold_uncertainty_score":0.4793283,"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."}}