{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117721,0.0002139129,0.0002348787,0.0003708131,0.0001348424,0.0003537112,0.0009482561,0.0002656505,0.000009264561],"category_scores_gemma":[0.0002418925,0.0002085931,0.00007287732,0.0003032227,0.00002254866,0.0003944803,0.001406497,0.001459478,0.0001284485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001188539,"about_ca_system_score_gemma":0.0001486901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008683115,"about_ca_topic_score_gemma":0.0004956714,"domain_scores_codex":[0.9980093,0.0001435486,0.0004596962,0.000719338,0.0003494738,0.0003186218],"domain_scores_gemma":[0.9987898,0.0001118567,0.0002210581,0.0007340539,0.00007211536,0.00007106016],"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":[0.000003882622,0.000013399,0.006276365,0.0000692023,0.000006677647,0.000002599239,0.0006709222,0.9432352,0.00002338874,0.02198803,0.0001320604,0.02757824],"study_design_scores_gemma":[0.0001576697,0.00001658875,0.01348954,0.00008569781,0.000003895967,0.000001864553,0.00008472762,0.9836733,0.000005989031,0.001691933,0.000593036,0.0001957106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007360579,0.00004955589,0.9855137,0.0007489395,0.0005654313,0.0002025081,0.000007163369,0.001297247,0.004254891],"genre_scores_gemma":[0.9659773,0.0002137883,0.03123314,0.00007276485,0.00007467156,0.00007041065,0.0005618526,0.000022271,0.00177379],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9586167,"threshold_uncertainty_score":0.8506179,"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."}}