{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001073834,0.001010677,0.0008967726,0.0009216918,0.0006675355,0.0011247,0.001478079,0.001197843,0.00459409],"category_scores_gemma":[0.004986337,0.0005147888,0.0009800382,0.0007473375,0.001516994,0.001650751,0.001496356,0.00136775,0.0006184092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417289,"about_ca_system_score_gemma":0.001218167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005725728,"about_ca_topic_score_gemma":0.007526932,"domain_scores_codex":[0.9994553,0.0001716626,0.00002515654,0.0001697083,0.0001057322,0.00007258989],"domain_scores_gemma":[0.9982128,0.001201618,0.000167703,0.0001335089,0.0001827108,0.0001018099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003947594,0.00002364136,0.0009619857,0.00005708939,0.00003176394,0.00007687729,0.00005365221,0.8982452,0.0006997754,0.06501122,0.001910191,0.03288923],"study_design_scores_gemma":[0.000006287077,0.000008585446,0.00007909687,0.000008449874,0.000005481532,0.00001674815,0.00000545414,0.9566417,0.0002149848,0.04196889,0.001039047,0.000005324671],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02119333,0.0004250195,0.9714049,0.0004247624,0.00006353966,0.00006239721,0.000299964,0.0007274234,0.005398662],"genre_scores_gemma":[0.7366094,0.000803386,0.2496124,0.0005447053,0.0001167198,0.0003360995,0.001405105,0.0003703722,0.01020185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005725728,"threshold_uncertainty_score":0.01536876,"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."}}