{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008463623,0.00156383,0.00129318,0.0007972642,0.0007561431,0.002270137,0.001347876,0.0026583,0.002255302],"category_scores_gemma":[0.03523804,0.0005150813,0.0007920624,0.0005918815,0.004143384,0.004714184,0.003522163,0.005144207,0.0004268383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001767004,"about_ca_system_score_gemma":0.00107723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008572514,"about_ca_topic_score_gemma":0.000932433,"domain_scores_codex":[0.9961826,0.001908461,0.0001752699,0.0005429076,0.0009762947,0.0002144807],"domain_scores_gemma":[0.9768202,0.01821774,0.001345902,0.00188408,0.001021886,0.0007101226],"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":[0.0001999622,0.0001045371,0.002391275,0.0001838714,0.00007638425,0.0001473508,0.0001576748,0.7354566,0.003889716,0.2211279,0.002788012,0.03347674],"study_design_scores_gemma":[0.00001998848,0.00009124512,0.0004887275,0.00003331148,0.000008960987,0.000100672,0.0000308288,0.8122905,0.002336203,0.1835539,0.001022985,0.00002265428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03830516,0.000396784,0.954595,0.00117608,0.00005497797,0.00005426423,0.0001264485,0.000298868,0.004992386],"genre_scores_gemma":[0.8661349,0.0004086016,0.1282076,0.0007061824,0.0000934906,0.0001811018,0.0004169483,0.0003359663,0.003515287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008463623,"threshold_uncertainty_score":0.04476047,"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."}}