{"id":"W2148186262","doi":"","title":"Wormholes Improve Contrastive Divergence","year":2003,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain Monte Carlo; Range (aeronautics); Statistical physics; Computer science; Markov chain; Divergence (linguistics); Markov chain mixing time; Distribution (mathematics); Sample (material); Monte Carlo method; Algorithm; Markov property; Artificial intelligence; Applied mathematics; Markov model; Mathematics; Statistics; Bayesian probability; Machine learning; Physics; Engineering; Mathematical analysis","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002622156,0.0001881613,0.0001858964,0.0001222838,0.0003095468,0.001316459,0.0005674329,0.00007849432,0.000007890718],"category_scores_gemma":[0.0001201965,0.0001533131,0.000040664,0.0005271067,0.00004874237,0.006937283,0.00006171633,0.0001585734,0.0001253122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004544295,"about_ca_system_score_gemma":0.0001719951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001560363,"about_ca_topic_score_gemma":6.558931e-7,"domain_scores_codex":[0.9985024,0.00004942388,0.0005205797,0.0002125783,0.0003696805,0.000345385],"domain_scores_gemma":[0.9988272,0.00003144151,0.0003935104,0.0002621312,0.0003669732,0.0001187961],"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":[0.00001623977,0.00006766975,0.002704238,0.001117616,0.00002507176,0.00001058528,0.005675781,0.001954059,0.0008709718,0.7020362,0.001535409,0.2839862],"study_design_scores_gemma":[0.001649518,0.0003326923,0.003679942,0.0005671159,0.00002491883,0.000391535,0.002060487,0.9195918,0.007304101,0.006954368,0.05590727,0.001536236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003796365,0.0005470279,0.9829984,0.000201801,0.001177575,0.0002835568,0.000005684989,0.0003217053,0.0106679],"genre_scores_gemma":[0.9965524,0.000007709911,0.002842475,0.0002575226,0.00003729607,0.00004644357,0.000003523259,0.000004971795,0.0002476731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.992756,"threshold_uncertainty_score":0.9997203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0106853115181344,"score_gpt":0.2217373375984179,"score_spread":0.2110520260802835,"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."}}