{"id":"W4391832947","doi":"10.48550/arxiv.2402.08018","title":"Nearest Neighbour Score Estimators for Diffusion Generative Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Alliance de recherche numérique du Canada; Compute Canada; Lawrence Berkeley National Laboratory; Canadian Institute for Advanced Research; U.S. Department of Energy","keywords":"Estimator; Econometrics; Diffusion; Generative grammar; Generative model; Statistics; Mathematics; Computer science; Artificial intelligence; Statistical physics; Geography; Physics; Thermodynamics","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":[0.0003233575,0.0004781563,0.0004777796,0.0003055191,0.0002384208,0.0003565061,0.001677464,0.0004426663,0.000009182027],"category_scores_gemma":[0.00002666679,0.0004787942,0.0004147683,0.000474622,0.00009469394,0.0003476012,0.003224044,0.0007244821,0.00003200342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001961889,"about_ca_system_score_gemma":0.0003818758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008572073,"about_ca_topic_score_gemma":0.00002628592,"domain_scores_codex":[0.9973385,0.0001509216,0.0002421876,0.001685917,0.0001122167,0.0004702221],"domain_scores_gemma":[0.9979799,0.0001429538,0.0001804209,0.001240041,0.0001980784,0.0002586435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001852234,0.00004865541,0.00002614034,0.0001606074,0.00007149007,0.000153847,0.0003754814,0.1181903,0.00006303506,0.8755135,0.0009080474,0.004470356],"study_design_scores_gemma":[0.0001658241,0.00003098394,0.00001076894,0.0001067457,0.00005320457,0.000002998945,0.0000057744,0.5202377,0.0001125559,0.4788808,0.000112666,0.0002800012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02739846,0.0002949047,0.9670487,0.0002940516,0.001429142,0.000685355,0.00006904134,0.0003750843,0.002405254],"genre_scores_gemma":[0.7062654,0.0001134383,0.2903625,0.0001872508,0.0002022649,0.000007180451,0.00002234638,0.00004445798,0.002795187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6788669,"threshold_uncertainty_score":0.9997663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1122222746815957,"score_gpt":0.223446374483258,"score_spread":0.1112240998016623,"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."}}