{"id":"W2891678505","doi":"10.48550/arxiv.1809.01818","title":"Improving Explorability in Variational Inference with Annealed Variational Objectives","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Inference; Robustness (evolution); Computer science; Mathematical optimization; Artificial intelligence; Machine learning; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002963297,0.0001386503,0.0001409703,0.0001323921,0.0001882351,0.00007835056,0.0004791489,0.00005496184,0.00006427027],"category_scores_gemma":[0.0001373647,0.0001343452,0.00003701782,0.0008855335,0.0001456971,0.00136404,0.0001806621,0.0001131803,0.00003134331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001307787,"about_ca_system_score_gemma":0.0002274156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002322696,"about_ca_topic_score_gemma":0.0003475468,"domain_scores_codex":[0.9987661,0.0001715427,0.0001288388,0.0005964859,0.00009122344,0.000245762],"domain_scores_gemma":[0.9989161,0.0002578968,0.0001057145,0.0003647598,0.0002783474,0.00007712955],"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":[0.0002216953,0.0003576862,0.09173792,0.00001284214,0.00007740906,0.00007004117,0.001798716,0.4446071,0.0008419466,0.4567344,0.00004877791,0.003491457],"study_design_scores_gemma":[0.0005227088,0.0001309817,0.09410264,0.00001029293,0.000006900638,0.000001308922,0.00006448659,0.891597,0.0002804203,0.01307427,0.00003280776,0.0001762091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09922659,0.000003624774,0.8992588,0.00008852703,0.0001233642,0.0001169292,0.000003026908,0.0000538349,0.001125326],"genre_scores_gemma":[0.9757516,0.000002657583,0.02393921,0.00007012884,0.0001204022,0.000001245612,0.000002650071,0.000005116475,0.0001069754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.876525,"threshold_uncertainty_score":0.5478439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04073361515774715,"score_gpt":0.1796875463963157,"score_spread":0.1389539312385685,"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."}}