{"id":"W3035564323","doi":"","title":"Undirected Graphical Models as Approximate Posteriors","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Graphical model; Computer science; Markov chain Monte Carlo; Estimator; Representation (politics); Undirected graph; Posterior probability; Markov chain; Algorithm; Backpropagation; Theoretical computer science; Artificial intelligence; Machine learning; Artificial neural network; Mathematics; Bayesian probability; Graph","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":[0.0001308182,0.0001742188,0.0001672669,0.00009121807,0.0001321133,0.0003455241,0.0008371493,0.00005276679,0.00032951],"category_scores_gemma":[0.0001710552,0.0001568189,0.00008376347,0.0002192025,0.00003819654,0.0004744602,0.0002589035,0.0004123201,0.0001418186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002171247,"about_ca_system_score_gemma":0.00004609314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007180668,"about_ca_topic_score_gemma":0.000004903399,"domain_scores_codex":[0.998589,0.0001644498,0.0002069196,0.000449584,0.0003880755,0.0002020014],"domain_scores_gemma":[0.999361,0.00006712776,0.0001085884,0.0001480638,0.000170687,0.0001445757],"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":[0.000167936,0.00008745526,0.0009611157,0.000009063269,0.0001471641,0.00008604627,0.001716174,0.1328033,0.01413498,0.7973547,0.0002510396,0.05228102],"study_design_scores_gemma":[0.0002533557,0.0001664787,0.0001743573,0.00002055746,0.000003601848,0.000006851666,0.00002749161,0.9881145,0.0007220601,0.008649821,0.001686634,0.0001742264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008224269,0.0000294983,0.9179032,0.02579958,0.0003550496,0.0001125684,0.000005723063,0.0003050205,0.04726504],"genre_scores_gemma":[0.9877242,0.00003944887,0.009626595,0.002116529,0.0001453234,0.000008054739,0.00002137062,0.00001237527,0.0003060883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9794999,"threshold_uncertainty_score":0.6394888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04728826431044014,"score_gpt":0.2723734905455278,"score_spread":0.2250852262350876,"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."}}