{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004011785,0.001160755,0.001282412,0.001860418,0.000837552,0.00153318,0.001949885,0.002346141,0.004142929],"category_scores_gemma":[0.01417805,0.0008924889,0.00189372,0.001228864,0.002062857,0.002943893,0.002588318,0.003152569,0.001015755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002693512,"about_ca_system_score_gemma":0.001931594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009592979,"about_ca_topic_score_gemma":0.007267018,"domain_scores_codex":[0.9988608,0.0003929337,0.00005806278,0.0003347808,0.0002612871,0.00009209204],"domain_scores_gemma":[0.9949051,0.003750538,0.000362707,0.000434614,0.0003494017,0.0001976509],"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":[0.00006439642,0.00004954813,0.001260687,0.00008641224,0.00003961764,0.00007485221,0.0001136887,0.8341947,0.001132164,0.110356,0.001927314,0.05070053],"study_design_scores_gemma":[0.000003125821,0.000006956519,0.00005457514,0.000005758639,0.000002068226,0.000008039407,0.000003588458,0.9700714,0.0001673727,0.02928233,0.0003892942,0.000005435929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005619896,0.0001978446,0.9927022,0.0002961319,0.00002885761,0.0000310801,0.0001152266,0.0003550776,0.0006536562],"genre_scores_gemma":[0.5172039,0.001069854,0.4684157,0.0008843471,0.0002924004,0.0005722725,0.00167739,0.0007264756,0.009157769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009592979,"threshold_uncertainty_score":0.02121657,"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."}}