{"id":"W2948700496","doi":"10.48550/arxiv.1906.02735","title":"Residual Flows for Invertible Generative Modeling","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Invertible matrix; Residual; Lipschitz continuity; Estimator; Discriminative model; Transformation (genetics); Density estimation; Mathematics; Computer science; Applied mathematics; Artificial neural network; Algorithm; Mathematical optimization; Artificial intelligence; Statistics; Pure mathematics","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":[0.000319185,0.0003916418,0.000458482,0.000206281,0.0002585889,0.0002321511,0.001619689,0.0003149197,0.00001797009],"category_scores_gemma":[0.00005845163,0.0004290767,0.0003017917,0.000321332,0.0000434134,0.0005633339,0.001660901,0.0003949433,0.00006608582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001755336,"about_ca_system_score_gemma":0.0003540805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001405328,"about_ca_topic_score_gemma":0.00008368489,"domain_scores_codex":[0.9975958,0.0001807907,0.0002436177,0.001409448,0.0001004876,0.0004698401],"domain_scores_gemma":[0.9979681,0.0001489,0.0001871998,0.001207017,0.0003440435,0.0001447763],"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":[0.00003039546,0.00003305607,0.00005158676,0.00003695093,0.0001109249,0.0000171594,0.0001770346,0.9746669,0.0001709337,0.02272703,0.001580457,0.0003975542],"study_design_scores_gemma":[0.00046449,0.00006359965,0.000006925772,0.00005469066,0.00006432664,7.694106e-7,0.00004597251,0.9645923,0.0009062986,0.03283821,0.0004764206,0.0004859836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02593243,0.0001195914,0.9705887,0.0002384929,0.00122939,0.0006822034,0.00003714241,0.0001450565,0.001027006],"genre_scores_gemma":[0.944014,0.0001219377,0.05308845,0.0002323823,0.000402124,0.00000459018,0.00003421072,0.00002845392,0.002073893],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9180815,"threshold_uncertainty_score":0.9998161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1108893237547569,"score_gpt":0.1968654022686914,"score_spread":0.08597607851393453,"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."}}