{"id":"W2990823792","doi":"10.48550/arxiv.1911.11791","title":"A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.000197303,0.0002433518,0.0003819768,0.0002764146,0.00008285819,0.00003256524,0.001545969,0.00007962239,0.00001068491],"category_scores_gemma":[0.00003056598,0.0001666048,0.0001177406,0.00093461,0.00008848694,0.0001580928,0.001484996,0.0002777356,0.000005499304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008058281,"about_ca_system_score_gemma":0.0001218922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001975464,"about_ca_topic_score_gemma":0.00004321482,"domain_scores_codex":[0.998431,0.0003213183,0.0002248997,0.0006485098,0.0002026298,0.0001716367],"domain_scores_gemma":[0.9974656,0.0003649533,0.0004803693,0.001420607,0.0002146812,0.00005379186],"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":[0.0002226142,0.001303336,0.006582676,0.00006375246,0.0004032887,0.00007810614,0.002569002,0.9583851,0.00002106527,0.02964639,0.0001918322,0.0005328938],"study_design_scores_gemma":[0.001795018,0.005354263,0.01530625,0.00033896,0.0004173077,0.000001055834,0.003837872,0.9651303,0.002642115,0.004382645,0.0001702946,0.0006239072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6618201,0.00004314685,0.3361125,0.00005433493,0.0001908308,0.0007697375,0.000005468185,0.00001764176,0.0009862876],"genre_scores_gemma":[0.9992309,0.00003650557,0.0004558088,0.00002924667,0.000024078,0.000001782103,0.000002135483,0.00001040844,0.0002091792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3374108,"threshold_uncertainty_score":0.6793945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07074209356704961,"score_gpt":0.1863141251924161,"score_spread":0.1155720316253665,"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."}}