{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006785023,0.0001164524,0.000140816,0.0001694193,0.0002280863,0.0001505088,0.0007857981,0.00006302823,0.000001454387],"category_scores_gemma":[0.0001919794,0.00009112858,0.00005067354,0.0008511688,0.00006420441,0.001411863,0.0004225198,0.0002755879,0.00001331337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003676368,"about_ca_system_score_gemma":0.00003283133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004350032,"about_ca_topic_score_gemma":0.00001141104,"domain_scores_codex":[0.9988921,0.00001435762,0.0002925584,0.0002633801,0.0002890065,0.0002485407],"domain_scores_gemma":[0.9994204,0.00003617004,0.000217455,0.0001634532,0.0001283875,0.00003411694],"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":[0.00009745991,0.00005652518,0.1876436,0.0004711867,0.00002630633,6.618738e-7,0.01690205,0.3191189,0.1728374,0.2949265,0.000681138,0.007238321],"study_design_scores_gemma":[0.0001634659,0.00004864406,0.01906263,0.0000665385,0.000004962461,0.0000067141,0.0004829391,0.9747,0.003371509,0.001075304,0.0009181225,0.00009919624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740704,0.00004590815,0.004871748,0.007885068,0.000405926,0.0003419074,0.000006328754,0.0008778461,0.01149485],"genre_scores_gemma":[0.9973531,0.0001016153,0.001585944,0.00003400763,0.00002908631,0.00002560011,0.000008586716,0.000009712941,0.0008523944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6555811,"threshold_uncertainty_score":0.3716116,"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."}}