{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03314105,0.001248935,0.001532543,0.002830373,0.001064,0.002959346,0.002976733,0.002842858,0.002060255],"category_scores_gemma":[0.1971425,0.001256816,0.001064818,0.002504816,0.003399613,0.004819785,0.00420851,0.004556602,0.0004428308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002273655,"about_ca_system_score_gemma":0.002898885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00709077,"about_ca_topic_score_gemma":0.006026129,"domain_scores_codex":[0.9836484,0.01060607,0.0008849821,0.001189014,0.003254722,0.0004168516],"domain_scores_gemma":[0.7705974,0.194282,0.00596775,0.02043837,0.007164033,0.001550469],"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":[0.0003701124,0.00007912009,0.01019265,0.000191409,0.0002515103,0.0001078774,0.0003085554,0.8688243,0.001291036,0.0782539,0.001290361,0.03883914],"study_design_scores_gemma":[0.00001251074,0.00001698913,0.0003204617,0.00001866994,0.00001091534,0.00002122718,0.00001893168,0.9693681,0.0007194445,0.02925193,0.0002290472,0.00001173922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06940558,0.0005710091,0.9255168,0.0006336141,0.00004096773,0.0000771879,0.0002417738,0.001516083,0.001996972],"genre_scores_gemma":[0.6629226,0.0003445915,0.334278,0.0002395986,0.00007378625,0.0002234214,0.0006644608,0.0007375997,0.0005159414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03314105,"threshold_uncertainty_score":0.1752688,"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."}}