{"id":"W7104448482","doi":"10.71781/10312","title":"Learning generative models from a control perspective","year":2025,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Institute for Catastrophic Loss Reduction; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generative grammar; Inference; Generative model; Probabilistic logic; Perspective (graphical); Generative Design; Graph; Statistical model","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002155612,0.0003303533,0.0005238489,0.0001106477,0.0003267591,0.001150661,0.001591482,0.0002187003,0.0004884831],"category_scores_gemma":[0.0001089558,0.0003133982,0.0001424457,0.0002589142,0.00001712046,0.0008900749,0.0002222827,0.0004374534,0.0001263829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001328663,"about_ca_system_score_gemma":0.0005310661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001203262,"about_ca_topic_score_gemma":0.001150431,"domain_scores_codex":[0.997918,0.0003197879,0.0002801006,0.0009803694,0.0002372981,0.0002644621],"domain_scores_gemma":[0.998578,0.0002146738,0.0002575527,0.0004430023,0.0004297538,0.00007708441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002973161,0.0001942421,0.0000103955,0.000008897674,0.001344362,0.00007472455,0.04932373,0.2086706,0.00400478,0.00876994,0.00324469,0.7240564],"study_design_scores_gemma":[0.001011186,0.000120647,0.00005447705,0.0002031314,0.0001567348,5.12306e-7,0.006009628,0.9614888,0.01041306,0.01224724,0.007657021,0.0006375232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00202208,0.0008874015,0.7569066,0.0004017284,0.001014274,0.000804782,0.00006753605,0.000008007485,0.2378876],"genre_scores_gemma":[0.6075621,0.000115568,0.2404624,0.0002407522,0.0006319729,0.0001779008,0.000620105,0.00004101427,0.1501482],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7528183,"threshold_uncertainty_score":0.9999318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02791182651700569,"score_gpt":0.2906971737876121,"score_spread":0.2627853472706064,"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."}}