{"id":"W4385849361","doi":"10.48550/arxiv.2308.07233","title":"A Unifying Generator Loss Function for Generative Adversarial Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generator (circuit theory); Divergence (linguistics); Discriminator; Function (biology); Mathematics; MNIST database; Alpha (finance); Combinatorics; Discrete mathematics; Applied mathematics; Pure mathematics; Topology (electrical circuits); Artificial neural network; Computer science; Physics; Power (physics); Artificial intelligence; Quantum mechanics; Optics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006485496,0.0005312712,0.0005209259,0.0003776209,0.0006148964,0.0002798465,0.001966412,0.0006310323,0.00001673092],"category_scores_gemma":[0.0001741401,0.0006454954,0.0004029702,0.0009091202,0.000122715,0.0005976289,0.002947188,0.001126547,0.00005321428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004533013,"about_ca_system_score_gemma":0.0003733557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000130181,"about_ca_topic_score_gemma":0.000067996,"domain_scores_codex":[0.9966576,0.0003340589,0.0003370198,0.001857627,0.0001459418,0.0006677643],"domain_scores_gemma":[0.9973239,0.0003932879,0.0004872121,0.001255263,0.0003306859,0.0002096013],"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":[0.0001083601,0.00002467206,0.0005135193,0.00004699882,0.0001845816,0.0001286784,0.0001466654,0.8431011,0.00001399616,0.1544372,0.0007717821,0.000522386],"study_design_scores_gemma":[0.001058349,0.00009020579,0.0001867558,0.00007101682,0.0001527028,0.00000236861,0.00006208324,0.9626409,0.00002408499,0.03417843,0.0008962505,0.0006367987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00899172,0.00005563439,0.9818366,0.0002207035,0.007052528,0.0007481556,0.00002295337,0.0008959689,0.0001757665],"genre_scores_gemma":[0.9714081,0.00008474434,0.02389314,0.0001901339,0.001962758,0.00001284637,0.0001310684,0.00008474812,0.002232409],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624164,"threshold_uncertainty_score":0.9995996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0937237138490774,"score_gpt":0.2186444265802673,"score_spread":0.1249207127311899,"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."}}