{"id":"W4409361642","doi":"10.1609/aaai.v39i25.34887","title":"Flow Factorization for Efficient Generative Flow Networks","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"University of Toronto","keywords":"Flow (mathematics); Computer science; Generative grammar; Artificial intelligence; Mathematics; Geometry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004322584,0.0002191238,0.0002370468,0.0001445496,0.0003212002,0.0003467316,0.001644957,0.0001100369,0.0000168156],"category_scores_gemma":[0.0006048456,0.0001694973,0.0001281395,0.0008102152,0.0001488098,0.0002012488,0.0003388976,0.0002378728,0.00001384445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008368578,"about_ca_system_score_gemma":0.0001239882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004868024,"about_ca_topic_score_gemma":0.000001621029,"domain_scores_codex":[0.9982836,0.00001717497,0.0005288025,0.0004610231,0.0003610306,0.0003484077],"domain_scores_gemma":[0.9981948,0.0001714934,0.0003255613,0.0002982669,0.0009567247,0.00005321383],"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":[0.00002041756,0.00002983749,0.00002663207,0.00001892667,0.00001273573,3.106793e-8,0.0003649156,0.5367439,0.001932945,0.4406297,0.000180977,0.02003905],"study_design_scores_gemma":[0.00003105017,0.0001094776,0.00003050232,0.0001395841,0.00001193023,2.55238e-7,0.00009284439,0.8445792,0.1342081,0.02051319,0.0001471058,0.0001367293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00117446,0.00001408981,0.990986,0.001817451,0.001248627,0.0006973515,0.000002624186,0.00009046893,0.003968944],"genre_scores_gemma":[0.9660493,0.00001618115,0.03271909,0.0002927939,0.00008486226,0.0000596413,0.000001990623,0.00001003889,0.0007660829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9648749,"threshold_uncertainty_score":0.6911898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05156236654893604,"score_gpt":0.2947704623131707,"score_spread":0.2432080957642346,"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."}}