{"id":"W2963702270","doi":"","title":"Measuring the reliability of MCMC inference with bidirectional Monte Carlo","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain Monte Carlo; Inference; Computer science; Bayesian inference; Monte Carlo method; Posterior probability; Approximate inference; Algorithm; Statistical inference; Artificial intelligence; Bayesian probability; Mathematics; Statistics","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":[0.001096885,0.0001329911,0.0002164104,0.00007175189,0.0001532005,0.00008676448,0.0001724937,0.00005980336,0.000002903218],"category_scores_gemma":[0.000921154,0.00005930589,0.00004692444,0.0002037735,0.00009438553,0.001138261,0.00003385969,0.00009798752,2.514142e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006545118,"about_ca_system_score_gemma":0.00009473554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008269923,"about_ca_topic_score_gemma":0.00001440047,"domain_scores_codex":[0.9985794,0.000138233,0.0005732968,0.0001037035,0.0004439517,0.0001614533],"domain_scores_gemma":[0.9980295,0.0004481029,0.0005289938,0.0002757739,0.0006734677,0.00004421995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00160419,0.0004167679,0.08814048,0.02308077,0.0003123499,0.000006234978,0.04163698,0.02452079,0.01337802,0.04378118,0.007028879,0.7560934],"study_design_scores_gemma":[0.01246388,0.001931919,0.01846037,0.01908196,0.0006236504,0.0008569804,0.02209461,0.7448647,0.05524463,0.005893647,0.114123,0.00436062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9120819,0.0001232444,0.08060244,0.0004972205,0.0004417317,0.0006082132,0.00002000028,0.0001781061,0.00544714],"genre_scores_gemma":[0.9982118,0.00000483016,0.001237413,0.00003019194,0.00005980402,0.0000630356,6.52693e-7,0.000008691925,0.0003835878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7517328,"threshold_uncertainty_score":0.2418424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07845018202371808,"score_gpt":0.3135058607120186,"score_spread":0.2350556786883006,"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."}}