{"id":"W7110672971","doi":"","title":"Improved off-policy training of diffusion samplers","year":2024,"lang":"en","type":"other","venue":"Jagiellonian University Repository (Jagiellonian University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Narodowym Centrum Nauki; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Benchmark (surveying); Sampling (signal processing); Inference; Sample (material); Diffusion; Training (meteorology); Code (set theory); Importance sampling; Base (topology); Quality (philosophy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004806529,0.001243701,0.001728453,0.0009473013,0.0007625413,0.001581784,0.003893964,0.002466199,0.005514523],"category_scores_gemma":[0.03058917,0.0008681559,0.0008608908,0.0008698244,0.001659814,0.003620228,0.002753556,0.003594,0.001175932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001860345,"about_ca_system_score_gemma":0.002458801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01020798,"about_ca_topic_score_gemma":0.01119179,"domain_scores_codex":[0.9984421,0.0006348181,0.00006504648,0.0003718559,0.0003251626,0.0001609391],"domain_scores_gemma":[0.9894197,0.007943556,0.0004485111,0.001045075,0.0007661748,0.0003769455],"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":[0.0002922823,0.0001922363,0.001839761,0.0001212604,0.00006384901,0.00007386046,0.0001398483,0.894777,0.001633586,0.02785026,0.003548433,0.06946757],"study_design_scores_gemma":[0.0000197295,0.00001090879,0.00003492753,0.000006045515,0.000002930178,0.000008576142,0.000004652556,0.9938815,0.0004060643,0.005385006,0.0002370598,0.000002706577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04729888,0.0006219004,0.9437682,0.00098497,0.0001655837,0.0001227852,0.0002209134,0.002860559,0.003956157],"genre_scores_gemma":[0.6438372,0.0003489737,0.3464017,0.0007887415,0.0001481272,0.0002820918,0.001044308,0.001012459,0.006136585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01020798,"threshold_uncertainty_score":0.02541971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109088682025203,"score_gpt":0.2008778014299251,"score_spread":0.1899689332274048,"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."}}