{"id":"W2593299827","doi":"10.48550/arxiv.1702.01691","title":"Calibrating Energy-based Generative Adversarial Networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Adversarial system; Generator (circuit theory); Computer science; Generative grammar; Energy (signal processing); Generative adversarial network; Artificial intelligence; Mathematical optimization; Theoretical computer science; Machine learning; Algorithm; Mathematics; Power (physics); Deep learning; 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":[0.002289556,0.001267942,0.0008167159,0.0006188231,0.0003425664,0.0008892014,0.001582346,0.001494556,0.002141961],"category_scores_gemma":[0.009645707,0.0006852827,0.0005290915,0.0004071851,0.001821115,0.001796536,0.003100404,0.00233524,0.0005532575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009598159,"about_ca_system_score_gemma":0.0005448145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001024173,"about_ca_topic_score_gemma":0.001006171,"domain_scores_codex":[0.999149,0.0003493144,0.00002771416,0.0002001434,0.0001943317,0.000079385],"domain_scores_gemma":[0.9971421,0.002143185,0.0001961925,0.0002859489,0.0001613591,0.00007128876],"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":[0.0000445474,0.00002237108,0.0004976102,0.0000347971,0.00002575136,0.00005021503,0.00004867151,0.9524351,0.002624798,0.02675528,0.0003859238,0.01707497],"study_design_scores_gemma":[0.000003082348,0.00001084402,0.0000512085,0.000005741365,0.000002805273,0.00001817031,0.000003959572,0.9884594,0.00067833,0.01050327,0.0002587609,0.000004411648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01089212,0.00011705,0.9870199,0.0001771713,0.00002221208,0.00002645328,0.00002326766,0.0001646682,0.001557091],"genre_scores_gemma":[0.8323683,0.0002863642,0.1624533,0.0003605849,0.00005902277,0.0001799994,0.0001678664,0.0001884862,0.003936117],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002289556,"threshold_uncertainty_score":0.0121085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04914877577270201,"score_gpt":0.1753241329017337,"score_spread":0.1261753571290317,"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."}}