{"id":"W3035170697","doi":"","title":"Semi-Supervised StyleGAN for Disentanglement Learning","year":2020,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Generalization; Generator (circuit theory); Controllability; Artificial intelligence; Representation (politics); Machine learning; External Data Representation; Feature learning; Unsupervised learning; Labeled data; Face (sociological concept); Identifiability; Semi-supervised learning; Mathematics; Power (physics)","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":[0.0002190633,0.0002741028,0.0004167928,0.0003816995,0.0001625112,0.00006541614,0.00120993,0.000273564,0.000006958603],"category_scores_gemma":[0.0009192341,0.0002680241,0.0001765191,0.00142046,0.0003149759,0.0005151269,0.0005434968,0.0003918145,0.00007612915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008479661,"about_ca_system_score_gemma":0.00009128438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004294409,"about_ca_topic_score_gemma":0.000003244769,"domain_scores_codex":[0.9979618,0.0000156306,0.0005522746,0.00065781,0.0003334276,0.000479082],"domain_scores_gemma":[0.9987826,0.00003155934,0.0002403522,0.0005409046,0.0001768089,0.000227791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000100475,0.0002036181,0.001116801,0.0004082491,0.0001446182,0.00005428865,0.0004252748,0.001111978,0.05406763,0.2601377,0.002268004,0.6799614],"study_design_scores_gemma":[0.001461887,0.001217724,0.00003108832,0.0001281262,0.00004633155,0.00002637486,0.0002116421,0.1227519,0.245,0.0164348,0.6120935,0.0005966107],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09262539,0.0001101439,0.8893177,0.0134847,0.001032892,0.0009003522,0.00006427911,0.001768639,0.0006958816],"genre_scores_gemma":[0.9002004,0.00001469066,0.09908636,0.0003241879,0.0001025642,0.0001630503,0.00003072121,0.00003066209,0.00004732177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.807575,"threshold_uncertainty_score":0.9999772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01959542504845665,"score_gpt":0.2369606785372796,"score_spread":0.217365253488823,"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."}}