{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002535704,0.0001610779,0.0001956845,0.00007687284,0.0002563092,0.00008781686,0.0002754584,0.0000459084,0.00004042048],"category_scores_gemma":[0.00003882968,0.0001232599,0.00009156056,0.0003584588,0.00008426501,0.0001275375,0.00009443048,0.0001636872,0.00001640048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001419238,"about_ca_system_score_gemma":0.00003134809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005431587,"about_ca_topic_score_gemma":0.000002251692,"domain_scores_codex":[0.9989069,0.000007411424,0.0003343521,0.000299005,0.0001700549,0.0002822673],"domain_scores_gemma":[0.9993361,0.00007132103,0.0001500453,0.00009665135,0.0002817744,0.00006408403],"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":[0.000157881,0.0000634243,0.0007084333,0.00009931924,0.00004280345,8.29023e-8,0.001259983,0.05825913,0.03376848,0.7888234,0.0006012417,0.1162158],"study_design_scores_gemma":[0.00002530457,0.00003833386,0.000006455557,0.0001047902,0.0000151389,5.702697e-7,0.00124262,0.8050587,0.04769548,0.1456381,0.00005292477,0.0001216048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9743925,0.00002452545,0.01974801,0.001653548,0.0004123734,0.0004903434,0.00001965451,0.00007471758,0.003184305],"genre_scores_gemma":[0.9990137,0.00004268669,0.0003089699,0.00003417939,0.0002125685,0.00005701148,0.00000346216,0.0000148694,0.0003125035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7467996,"threshold_uncertainty_score":0.5026394,"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."}}