{"id":"W2773981138","doi":"","title":"Parametric Adversarial Divergences are Good Task Losses for Generative Modeling","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parametric statistics; Generative grammar; Machine learning; Artificial intelligence; Task (project management); Divergence (linguistics); Nonparametric statistics; Generator (circuit theory); Adversarial system; Parametric model; Generative model; Mathematics; Econometrics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004115714,0.0005756033,0.0007081148,0.0003572608,0.001071086,0.0006357516,0.003335033,0.0004302304,0.00001916333],"category_scores_gemma":[0.0003243063,0.0006063913,0.000556401,0.0004361132,0.0001786331,0.001030954,0.00246668,0.000480866,0.00003364027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001967635,"about_ca_system_score_gemma":0.000359447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004241645,"about_ca_topic_score_gemma":0.000152436,"domain_scores_codex":[0.9967708,0.0002304573,0.0003259702,0.001868854,0.0001793999,0.0006245286],"domain_scores_gemma":[0.9964901,0.0002715818,0.000746233,0.001680721,0.0005743402,0.0002369796],"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":[0.0000490132,0.00008024599,0.0005679207,0.00004337964,0.0002587988,0.0000696003,0.0001420425,0.9792566,0.00002309954,0.01781169,0.000692144,0.001005524],"study_design_scores_gemma":[0.0006070227,0.00007953975,0.0001006319,0.0000769285,0.0001752149,0.000001226639,0.0001083181,0.9513955,0.0002770793,0.04590421,0.000585306,0.0006890651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01994087,0.0003471649,0.974799,0.0002120244,0.002961269,0.0007086631,0.0001236097,0.0001549101,0.0007524343],"genre_scores_gemma":[0.9792404,0.0005324722,0.01829631,0.00007131194,0.000806124,0.000008657579,0.00003295043,0.00002781922,0.0009839396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9592996,"threshold_uncertainty_score":0.9996387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1197481016970471,"score_gpt":0.2172347167424082,"score_spread":0.09748661504536113,"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."}}