{"id":"W4321472417","doi":"10.48550/arxiv.2302.09465","title":"Stochastic Generative Flow Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Genentech; Canadian Institute for Advanced Research","keywords":"Computer science; Probabilistic logic; Inference; Variety (cybernetics); Stochastic modelling; Limit (mathematics); Generative grammar; Sample (material); Flow (mathematics); Stochastic dynamics; Mathematical optimization; Artificial intelligence; Mathematics; Statistical physics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002682215,0.0003753985,0.0003490123,0.0002790173,0.0002241193,0.0002489618,0.002386869,0.000345948,0.00002601045],"category_scores_gemma":[0.0000721656,0.0004469584,0.0002101591,0.00074909,0.0001060172,0.000283663,0.003756718,0.0009833194,0.0004441723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002580833,"about_ca_system_score_gemma":0.0001934397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004432938,"about_ca_topic_score_gemma":0.00001472084,"domain_scores_codex":[0.9977921,0.000154836,0.0002334748,0.001170651,0.0001343074,0.0005145923],"domain_scores_gemma":[0.9976714,0.0002073834,0.0002802161,0.00148612,0.0001692829,0.000185608],"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":[0.000005499157,0.00001142643,0.0001075161,0.00001714202,0.00009420828,0.0001948756,0.0001555678,0.9584777,0.000001116691,0.03974622,0.001037102,0.0001515847],"study_design_scores_gemma":[0.0002312744,0.00004624134,0.0001783116,0.00007764396,0.00004552607,0.000001955459,0.00002266908,0.9930077,0.000003817523,0.005859418,0.00008224419,0.0004432347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00099639,0.00002597465,0.9947692,0.0001149049,0.00220636,0.0003158554,0.000004174545,0.0007769421,0.000790186],"genre_scores_gemma":[0.9767625,0.00007921467,0.01059933,0.0001357977,0.0002572887,0.000001914224,0.00004429471,0.00004242183,0.01207729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9841699,"threshold_uncertainty_score":0.9997982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1006484747966427,"score_gpt":0.1961954786015142,"score_spread":0.09554700380487152,"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."}}