{"id":"W4398850169","doi":"10.48550/arxiv.2405.14664","title":"Fisher Flow Matching for Generative Modeling over Discrete Data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Engineering and Physical Sciences Research Council; Center for Evolutionary and Theoretical Immunology","keywords":"Matching (statistics); Flow (mathematics); Computer science; Generative grammar; Generative model; Mathematics; Econometrics; Algorithm; Artificial intelligence; Statistics; Geometry","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0003820933,0.0003841922,0.0003369712,0.0002123043,0.0001948028,0.0006083348,0.003861013,0.0002563518,0.00002475633],"category_scores_gemma":[0.00004650881,0.0004183355,0.0001944686,0.0003095222,0.00004615232,0.0007111225,0.01174879,0.0008470593,0.0000784116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002139321,"about_ca_system_score_gemma":0.0002443162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009918404,"about_ca_topic_score_gemma":0.0000233966,"domain_scores_codex":[0.9973812,0.00008113631,0.0002677704,0.001689816,0.0001489539,0.0004311976],"domain_scores_gemma":[0.9968861,0.0001227508,0.0001709062,0.002580183,0.0001137452,0.0001263091],"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":[0.000009443727,0.000007532748,0.00001950547,0.0001399263,0.0001527847,0.00008119994,0.0003644479,0.9381698,0.00000885168,0.05962231,0.001257689,0.0001665173],"study_design_scores_gemma":[0.0002283756,0.00002421666,0.000003801642,0.0001722915,0.0001125488,0.000001381182,0.00004155367,0.9442938,0.000008638495,0.05405101,0.0006078,0.0004545694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006708623,0.00007297027,0.9889687,0.0002001205,0.001508408,0.0004688925,0.00009152482,0.000343045,0.001637754],"genre_scores_gemma":[0.8880226,0.00008468769,0.1045141,0.0001866821,0.0003137579,0.000001994188,0.0003064329,0.00005835283,0.006511385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8844545,"threshold_uncertainty_score":0.9998268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1533595816020156,"score_gpt":0.2388246567827831,"score_spread":0.08546507518076751,"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."}}