{"id":"W3159062657","doi":"","title":"Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Machine learning; Bayesian probability; Benchmark (surveying); Artificial intelligence; Gaussian process; Regression; Consistency (knowledge bases); Benchmarking; Marginal likelihood; Statistics; Mathematics; Gaussian","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":[0.0002181516,0.0002296578,0.0002065352,0.000139074,0.0002677079,0.0008802247,0.0004757612,0.00008471689,0.0001608484],"category_scores_gemma":[0.000400759,0.0002092859,0.0000399389,0.0001984042,0.0001345428,0.0003903621,0.0001974805,0.0003348924,0.00002595637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006227293,"about_ca_system_score_gemma":0.0002668548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007061971,"about_ca_topic_score_gemma":0.0001911155,"domain_scores_codex":[0.9981817,0.0001533939,0.0003299856,0.0005527885,0.0005158476,0.0002662938],"domain_scores_gemma":[0.9983075,0.0003400721,0.0001840338,0.0002759027,0.0007324762,0.0001599785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004891743,0.000056573,0.00004636064,0.000005994243,0.00002302107,0.00011295,0.0006875971,0.009800689,0.0002619245,0.7289178,0.0002299136,0.2598082],"study_design_scores_gemma":[0.000038477,0.0001270778,0.0001275696,0.00007658726,0.000007113647,0.00005737256,0.0002807815,0.6956477,0.0006063792,0.3027677,0.0001006897,0.0001625856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001279013,0.00003343638,0.9817572,0.01108069,0.001001138,0.0001038258,0.0003508551,0.00007901502,0.004314845],"genre_scores_gemma":[0.9065931,0.0001016348,0.09163354,0.0003700146,0.0001281405,0.00001501228,0.0001814853,0.00001176381,0.0009652841],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9053141,"threshold_uncertainty_score":0.8534431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08572084720730128,"score_gpt":0.3550802520154215,"score_spread":0.2693594048081202,"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."}}