{"id":"W3103390726","doi":"","title":"Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Flexibility (engineering); Computer science; Software; Fuzz testing; Autoregressive model; Function (biology); Energy (signal processing); Partition function (quantum field theory); Machine learning; Artificial intelligence; Algorithm; Mathematics; Programming language","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":[0.0001416918,0.0001378919,0.0001256587,0.00007820834,0.0002272221,0.00009132401,0.0006216684,0.00007229951,0.00002510141],"category_scores_gemma":[0.00003433505,0.0001537731,0.00005381633,0.0007969157,0.00004840023,0.001545566,0.0001697276,0.0002219171,0.00007935066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005412285,"about_ca_system_score_gemma":0.00008452165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001606245,"about_ca_topic_score_gemma":0.000009484008,"domain_scores_codex":[0.9987888,0.0001841031,0.0001223659,0.0006014322,0.00009142594,0.0002118235],"domain_scores_gemma":[0.9991838,0.00006367578,0.00010873,0.0003961719,0.00006991089,0.0001777252],"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":[0.00001851978,0.00001370902,0.0002083703,0.000006838008,0.000005505939,0.00001379386,0.0001096669,0.6933223,0.0001925979,0.3034391,0.00009685777,0.002572736],"study_design_scores_gemma":[0.0003470464,0.0001077245,0.00004161178,0.000008172095,0.00001155795,6.425132e-7,0.00007377654,0.9833086,0.000214013,0.01111442,0.004590674,0.0001817593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001713323,0.000009962202,0.9940276,0.001051229,0.00005688427,0.00004840541,0.000001936859,0.0003823538,0.002708265],"genre_scores_gemma":[0.9930169,0.0000119757,0.005907288,0.0004810341,0.00004043336,7.163352e-7,0.0000664458,0.00001051328,0.0004647235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9913036,"threshold_uncertainty_score":0.6270686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0675045391712458,"score_gpt":0.1742403597032125,"score_spread":0.1067358205319667,"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."}}