{"id":"W4388521737","doi":"10.1609/aaaiss.v1i1.27492","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Machine learning; Artificial intelligence; Probabilistic logic; Computer science; Conformal map; Context (archaeology); Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009051367,0.001090131,0.001346324,0.001622806,0.0007996389,0.002656984,0.0019839,0.001780059,0.001073039],"category_scores_gemma":[0.04952371,0.0008947081,0.0008186677,0.001087129,0.003466214,0.005357177,0.005236556,0.003494095,0.0001156268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002477624,"about_ca_system_score_gemma":0.001636697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003360189,"about_ca_topic_score_gemma":0.002662487,"domain_scores_codex":[0.9960289,0.00147129,0.0002264862,0.0006245942,0.001416737,0.0002320187],"domain_scores_gemma":[0.968815,0.0247501,0.002285329,0.002344056,0.001312349,0.0004931513],"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":[0.00008856399,0.00002478159,0.002531772,0.0001175527,0.00007033502,0.00008545772,0.0001344694,0.8791285,0.0009550838,0.09735652,0.0005584101,0.01894858],"study_design_scores_gemma":[0.000004730219,0.00001793088,0.000326736,0.00003188065,0.000008227343,0.00002275422,0.00001160717,0.9107679,0.0007753288,0.08775862,0.0002601873,0.00001403715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04592215,0.0007520239,0.9503687,0.0009141344,0.00003546895,0.00002702566,0.0001746047,0.0002024688,0.001603519],"genre_scores_gemma":[0.9102538,0.000740741,0.08730605,0.0003665792,0.0001110781,0.0001060417,0.0003654298,0.0001357203,0.0006145041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009051367,"threshold_uncertainty_score":0.04786879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02276653752474929,"score_gpt":0.2509755326799586,"score_spread":0.2282089951552094,"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."}}