{"id":"W2963645527","doi":"","title":"GumBolt: Extending Gumbel trick to Boltzmann priors","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Prior probability; Gumbel distribution; Artificial intelligence; Computer science; MNIST database; Algorithm; Latent variable; Margin (machine learning); Bayesian probability; Mathematics; Machine learning; Artificial neural network; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004267985,0.0001855149,0.0002094771,0.0002489257,0.0005136473,0.001516733,0.0006517376,0.00006792678,0.000007777092],"category_scores_gemma":[0.0001208954,0.0001581012,0.00004952845,0.0008827785,0.00004153391,0.005761241,0.0001663932,0.0001007219,0.0004208765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006956558,"about_ca_system_score_gemma":0.00006896163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000490265,"about_ca_topic_score_gemma":0.00000259418,"domain_scores_codex":[0.9983588,0.00006896147,0.0005602142,0.0002340789,0.0004031903,0.0003747116],"domain_scores_gemma":[0.9987161,0.00003152088,0.0002877529,0.0003398148,0.0004711455,0.0001536716],"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":[0.00003348763,0.00003977269,0.0003277783,0.0002558024,0.00002726701,0.000004369766,0.01441784,0.02257657,0.002574618,0.004953614,0.03315462,0.9216343],"study_design_scores_gemma":[0.0002279232,0.0001267888,0.0006521105,0.0001125037,0.000005647515,0.00003263748,0.0003255646,0.913408,0.001775316,0.00004057482,0.08300981,0.000283062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008259667,0.0001320825,0.9818231,0.0006892149,0.001980285,0.0003897877,0.000002487679,0.0003079911,0.00641531],"genre_scores_gemma":[0.9873005,0.000002456826,0.01055511,0.001070485,0.0005976596,0.00003745631,0.000004190863,0.000008510116,0.0004236143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790409,"threshold_uncertainty_score":0.9995198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01642140205776399,"score_gpt":0.256894679725335,"score_spread":0.240473277667571,"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."}}