{"id":"W3037834087","doi":"","title":"Structured Conditional Continuous Normalizing Flows for Efficient Amortized Inference in Graphical Models.","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Graphical model; Computer science; Inference; Amortized analysis; Theoretical computer science; Programming language; Data structure; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0001406835,0.000169115,0.0002030721,0.00009904407,0.0001181538,0.0002836307,0.0005381268,0.00006456249,0.00005228298],"category_scores_gemma":[0.0002713662,0.0001633796,0.00004178528,0.0002136869,0.0001087743,0.0001663522,0.000105641,0.0002050219,0.00001295774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002206871,"about_ca_system_score_gemma":0.00007334047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002530082,"about_ca_topic_score_gemma":0.00009195997,"domain_scores_codex":[0.9984695,0.00004114528,0.0004809261,0.0004578092,0.0003116913,0.0002389373],"domain_scores_gemma":[0.9987129,0.0005745549,0.0001245441,0.0001379375,0.0003034368,0.0001466497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007382457,0.00005054833,0.00002882091,0.000005667658,0.000008753158,0.00000797004,0.0003070382,0.04689566,0.0007374883,0.9165722,0.00008298679,0.03522907],"study_design_scores_gemma":[0.0000643106,0.00008061301,0.00008468115,0.00001370172,0.000002602867,0.000001752535,0.00006926053,0.6352476,0.0003956905,0.363822,0.00009919937,0.0001185089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007379238,0.00001282239,0.986497,0.004858078,0.0002123415,0.0003220612,0.0003211446,0.00004932939,0.0003479977],"genre_scores_gemma":[0.9439371,0.0000528346,0.05481153,0.0009266777,0.00009549993,0.00006975506,0.00009195265,0.000007138407,0.000007516584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9365578,"threshold_uncertainty_score":0.6662426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.116448737573174,"score_gpt":0.3425164012567682,"score_spread":0.2260676636835943,"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."}}