{"id":"W3045177652","doi":"","title":"Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Information bottleneck method; Computer science; Generative model; Artificial intelligence; Latent variable; Machine learning; Generative grammar; Dependency (UML); Latent variable model; Graphical model; Inductive bias; Flexibility (engineering); Multi-task learning; Mathematics; Mutual information","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006366405,0.00134516,0.00154189,0.001697503,0.0006884827,0.002024647,0.002961059,0.002064452,0.00303612],"category_scores_gemma":[0.01803002,0.001131845,0.001978421,0.001292553,0.005018185,0.004368627,0.003851712,0.004780195,0.0006045019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00189899,"about_ca_system_score_gemma":0.00146719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001396008,"about_ca_topic_score_gemma":0.001983274,"domain_scores_codex":[0.9969819,0.001630503,0.00008874174,0.0006133356,0.0005195293,0.0001659993],"domain_scores_gemma":[0.9883345,0.008522592,0.0009153592,0.001522359,0.000395557,0.0003096433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004291567,0.00004513538,0.0009075328,0.0001031579,0.00009751947,0.0001046759,0.0002335227,0.2277443,0.00141314,0.7494155,0.001451346,0.0184413],"study_design_scores_gemma":[0.00001070391,0.00001901428,0.0001545014,0.0000244854,0.00001465178,0.00004676346,0.00001530363,0.5789748,0.0003883795,0.4194312,0.0009040401,0.00001613269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002857398,0.00009417297,0.9958467,0.0003722958,0.00001260292,0.0000196238,0.00007218488,0.00008565409,0.0006394601],"genre_scores_gemma":[0.5387134,0.001093091,0.4502673,0.00102139,0.0003760127,0.0007203296,0.0007697914,0.0004812123,0.006557469],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006366405,"threshold_uncertainty_score":0.03366917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07586395186275015,"score_gpt":0.2021338429454234,"score_spread":0.1262698910826733,"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."}}