{"id":"W3184623357","doi":"10.48550/arxiv.2106.13435","title":"NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image\\n Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Artificial intelligence; MNIST database; Interpretability; Parsing; Image (mathematics); Parametric statistics; Generative model; Heuristics; Variable (mathematics); Latent variable model; Machine learning; Dependency grammar; Generative grammar; Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009336882,0.000783038,0.000727366,0.0004834602,0.0003302525,0.0009457006,0.002509746,0.001429617,0.007384659],"category_scores_gemma":[0.003195487,0.0006540446,0.001012939,0.0005219106,0.001061817,0.001794023,0.001801951,0.002692636,0.001941528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000894634,"about_ca_system_score_gemma":0.0007035254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00192002,"about_ca_topic_score_gemma":0.004261964,"domain_scores_codex":[0.9995064,0.0001648886,0.00001438426,0.0001504672,0.0001215803,0.00004232393],"domain_scores_gemma":[0.9992124,0.0004792001,0.00005356177,0.0001558184,0.000061946,0.00003708063],"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":[0.0001556175,0.00008222535,0.0007685461,0.00013924,0.00008247313,0.0001896988,0.0001534099,0.6835862,0.005560748,0.1041619,0.01034784,0.194772],"study_design_scores_gemma":[0.000009440656,0.0000147678,0.00005203698,0.000006883462,0.000006492937,0.00003910402,0.000004992752,0.9736432,0.001154294,0.02305383,0.002008664,0.000006183362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00246587,0.000144063,0.995005,0.0001682649,0.00002951594,0.00003726947,0.0001520704,0.0007235421,0.001274481],"genre_scores_gemma":[0.3655693,0.0005654588,0.6097293,0.0008517781,0.0001466437,0.0005042432,0.001556466,0.0009364753,0.02014028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007384659,"threshold_uncertainty_score":0.02470416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07431892535437394,"score_gpt":0.1919909476839597,"score_spread":0.1176720223295858,"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."}}