{"id":"W4382239200","doi":"10.1609/aaai.v37i6.25834","title":"Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Uncertainty quantification; Computer science; Measurement uncertainty; Benchmark (surveying); Robustness (evolution); Artificial intelligence; Machine learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003498445,0.001528693,0.001044883,0.0015924,0.0008610008,0.001572696,0.001461724,0.001336307,0.001332632],"category_scores_gemma":[0.0126039,0.000626304,0.001076523,0.0007183309,0.001376975,0.003524061,0.002358735,0.002653562,0.0002890123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001213999,"about_ca_system_score_gemma":0.001284728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00506021,"about_ca_topic_score_gemma":0.005815996,"domain_scores_codex":[0.9990985,0.0003140783,0.00004337103,0.0002187591,0.0002432712,0.00008194707],"domain_scores_gemma":[0.9963579,0.002131444,0.0003615294,0.0005485752,0.0004631101,0.0001374731],"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":[0.00004628866,0.00003434656,0.001773748,0.00003507399,0.0000536045,0.00004102329,0.00009095731,0.9253731,0.001482843,0.02145663,0.000717686,0.04889471],"study_design_scores_gemma":[0.000001897685,0.000008478821,0.0001307491,0.000006783418,0.000004255704,0.00001034866,0.000006019555,0.9859737,0.0005866427,0.01288376,0.0003804777,0.000006850019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01437373,0.0001029046,0.9840968,0.0001178497,0.00002654684,0.0000227617,0.00007429059,0.0004180734,0.0007671929],"genre_scores_gemma":[0.667061,0.0002916871,0.3289682,0.0002637529,0.000156035,0.0001983703,0.0007264786,0.0003951656,0.001939319],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00506021,"threshold_uncertainty_score":0.01850182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09900523982385097,"score_gpt":0.3062980052594437,"score_spread":0.2072927654355928,"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."}}