{"id":"W7162310612","doi":"10.3997/2214-4609.202510306","title":"Enhancing Uncertainty Quantification Performance via Deep Learning-Assisted Markov Chain Monte Carlo","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Monte Carlo method; Markov chain Monte Carlo; Uncertainty quantification; Markov chain; Uncertainty analysis; Measurement uncertainty","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003118967,0.0008359024,0.0008688944,0.0007478351,0.002039057,0.0007981979,0.002405949,0.00050388,0.0003092845],"category_scores_gemma":[0.001159125,0.0008825922,0.0003243958,0.003166811,0.0003100505,0.001380932,0.001406808,0.002096775,0.0002170643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007916873,"about_ca_system_score_gemma":0.0005270329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001235526,"about_ca_topic_score_gemma":0.000653639,"domain_scores_codex":[0.9928163,0.001267906,0.001578058,0.002012499,0.0009560687,0.001369113],"domain_scores_gemma":[0.995663,0.0007787485,0.0008516589,0.001762846,0.0006812463,0.00026253],"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":[0.0001061144,0.000106682,0.004909225,0.0002768346,0.0001164138,0.00001576639,0.001551091,0.5239978,0.001730478,0.003668675,0.00005793306,0.4634629],"study_design_scores_gemma":[0.0009339271,0.0001848063,0.02573877,0.0004642473,0.000100687,0.00002120868,0.0005099801,0.9668493,0.00191049,0.00008029232,0.002378077,0.0008282411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06804316,0.0007327875,0.9159883,0.00189426,0.003663848,0.0007110029,8.617754e-7,0.0006255847,0.008340217],"genre_scores_gemma":[0.9433231,0.0001851723,0.03109868,0.0003943157,0.0002393611,0.00006105215,0.00001096629,0.00005220325,0.02463512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8848896,"threshold_uncertainty_score":0.9993625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01120442573902244,"score_gpt":0.2595734411563984,"score_spread":0.248369015417376,"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."}}