{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000301078,0.0004314691,0.0005077779,0.0003186408,0.000318327,0.0006094867,0.001313226,0.000371419,0.00002964422],"category_scores_gemma":[0.00009810676,0.0004857772,0.0003470828,0.0009905582,0.00006258566,0.000742499,0.001351838,0.0003952602,0.000009366529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002507975,"about_ca_system_score_gemma":0.0005215309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001348265,"about_ca_topic_score_gemma":0.00005381192,"domain_scores_codex":[0.997389,0.000143606,0.0002939188,0.001554306,0.000130626,0.0004885942],"domain_scores_gemma":[0.9974948,0.0001068048,0.0003059151,0.001275097,0.0006324794,0.0001849662],"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":[0.00001426013,0.00006290881,0.00003985158,0.00004451132,0.0001332128,0.00003992805,0.0001319456,0.9878236,0.002386715,0.007259318,0.001612564,0.0004511758],"study_design_scores_gemma":[0.0005290023,0.00003620602,0.0000567435,0.00002879837,0.0001303244,0.000003329485,0.00001444389,0.9845688,0.002229381,0.01179449,0.00009667661,0.0005117814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02172302,0.00008194246,0.9758943,0.00009950986,0.001120288,0.0006285526,0.00004715263,0.0001085843,0.0002966631],"genre_scores_gemma":[0.7469997,0.00009014139,0.2510958,0.0001458349,0.0002306028,0.000006189465,0.0000954198,0.00002393628,0.001312348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7252767,"threshold_uncertainty_score":0.9997594,"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."}}