{"id":"W3103036192","doi":"","title":"Wavelet Flow: Fast Training of High Resolution Normalizing Flows","year":2020,"lang":"en","type":"article","venue":"York University Digital Library (York University)","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Wavelet; Computer science; Flow (mathematics); Probabilistic logic; Wavelet transform; Algorithm; Dimension (graph theory); Artificial intelligence; Pattern recognition (psychology); 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":[0.00006294014,0.0002437383,0.0003557444,0.000424232,0.0003139717,0.0002641731,0.001697748,0.0001374643,0.0000493878],"category_scores_gemma":[0.00002812832,0.0003073302,0.0002263752,0.002272552,0.0001409898,0.006230125,0.00096377,0.0002707979,0.00005161826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006359439,"about_ca_system_score_gemma":0.0002468424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002895344,"about_ca_topic_score_gemma":0.000001714154,"domain_scores_codex":[0.9983391,0.0001797249,0.0001904539,0.0005605253,0.0003127437,0.0004174334],"domain_scores_gemma":[0.9989104,0.0001509861,0.0001703075,0.0003844891,0.00005010515,0.000333679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003384562,0.0006829744,0.002846813,0.0004539227,0.0007875158,0.007961352,0.02900481,0.01826034,0.004034426,0.505801,0.05404884,0.3727334],"study_design_scores_gemma":[0.005540092,0.0008985028,0.001122175,0.0002851558,0.0001358146,0.00005930586,0.01028874,0.1138375,0.004207585,0.001592256,0.8603107,0.00172213],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03559557,0.0000705395,0.8523654,0.001441168,0.0002448554,0.0002058678,0.000270458,0.0008178537,0.1089883],"genre_scores_gemma":[0.8259058,0.00002615223,0.1670835,0.0003682377,0.0001262096,3.182546e-8,0.0001125383,0.00002637289,0.006351141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8062619,"threshold_uncertainty_score":0.9999379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02602066930924904,"score_gpt":0.1754915263495752,"score_spread":0.1494708570403262,"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."}}