{"id":"W4386708427","doi":"10.32920/24132882.v1","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Probabilistic logic; Conformal map; Machine learning; Artificial intelligence; Context (archaeology); Computer science; Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Data mining; Mathematics; Simulation","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":[0.00808001,0.001024381,0.001263073,0.001384774,0.0007520227,0.002568662,0.001823033,0.001761799,0.001273332],"category_scores_gemma":[0.04173917,0.0008467654,0.0007963352,0.0009614221,0.003372515,0.004644579,0.004863539,0.003569066,0.0001402682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002522053,"about_ca_system_score_gemma":0.001446791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00370179,"about_ca_topic_score_gemma":0.002624847,"domain_scores_codex":[0.9965824,0.001317188,0.0001814164,0.0005540805,0.0011652,0.0001996386],"domain_scores_gemma":[0.9751076,0.01951614,0.001831526,0.001964885,0.001123875,0.0004559986],"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":[0.00009364066,0.00002434887,0.002377746,0.0001194413,0.00006652933,0.00008836378,0.000129801,0.8529546,0.0009973317,0.1199249,0.0008343034,0.02238897],"study_design_scores_gemma":[0.000003866518,0.00001345325,0.0002586529,0.00002652987,0.000005979268,0.00001735559,0.000008743801,0.9229754,0.0007005114,0.07571974,0.0002589222,0.00001079582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04195753,0.0007329624,0.9538588,0.0010744,0.00003931238,0.00002680519,0.0001859604,0.0002416937,0.001882551],"genre_scores_gemma":[0.9026062,0.0007397893,0.09437731,0.0004378599,0.0001213878,0.0001109456,0.0004297862,0.0001729989,0.001003694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00808001,"threshold_uncertainty_score":0.04273164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0937607704171857,"score_gpt":0.3228173958105193,"score_spread":0.2290566253933336,"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."}}