{"id":"W4391766501","doi":"10.48550/arxiv.2402.06121","title":"Iterated Denoising Energy Matching for Sampling from Boltzmann Densities","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Electron and X-Ray Spectroscopy Techniques","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Samsung; Nvidia","keywords":"Matching (statistics); Sampling (signal processing); Iterated function; Energy (signal processing); Statistical physics; Boltzmann constant; Noise reduction; Mathematics; Computer science; Statistics; Physics; Artificial intelligence; Mathematical analysis; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002803351,0.0009567463,0.001287061,0.001002063,0.0006307329,0.001162568,0.00270074,0.001995425,0.002953711],"category_scores_gemma":[0.01252639,0.0008152075,0.001092695,0.0006659672,0.001532577,0.00187011,0.002194489,0.002113956,0.0008201287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519379,"about_ca_system_score_gemma":0.001582138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004239861,"about_ca_topic_score_gemma":0.004692124,"domain_scores_codex":[0.9990184,0.0003610173,0.00004776522,0.000192503,0.0002968018,0.00008353656],"domain_scores_gemma":[0.9972358,0.001774389,0.00018755,0.0003042762,0.0003384855,0.0001595305],"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":[0.0001597095,0.0001016121,0.002206901,0.0001301652,0.00008230929,0.00009246396,0.0001324821,0.8598624,0.003770876,0.06155431,0.001793191,0.07011364],"study_design_scores_gemma":[0.000007605581,0.000009806618,0.00005067852,0.00000425958,0.000002360622,0.0000111179,0.00000459085,0.9892659,0.0005982307,0.009785959,0.0002554502,0.000004015416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01547692,0.0001443581,0.9823137,0.0001921439,0.00003271439,0.00005349769,0.00004602026,0.0006238254,0.001116826],"genre_scores_gemma":[0.4288957,0.0002194663,0.5642301,0.0005146673,0.00009616337,0.0004555475,0.0006062632,0.0006804132,0.004301634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004239861,"threshold_uncertainty_score":0.01482576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05687917568195515,"score_gpt":0.2276072367513422,"score_spread":0.170728061069387,"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."}}