{"id":"W4376272403","doi":"10.1093/mnrasl/slad152","title":"Posterior sampling of the initial conditions of the universe from non-linear large scale structures using score-based generative models","year":2023,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society Letters","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Perimeter Institute; Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Centre for Research in Astrophysics of Québec","funders":"Vermont Agency of Natural Resources; Institut Lagrange de Paris; Fonds de recherche du Québec; National Aeronautics and Space Administration; Agence Nationale de la Recherche; Canada Research Chairs; Alliance de recherche numérique du Canada; Flatiron Health","keywords":"Physics; Universe; Inference; Cosmology; Field (mathematics); Sampling (signal processing); Statistical physics; Astrophysics; Artificial intelligence; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004271389,0.0008882614,0.001175023,0.001459614,0.0006636648,0.002258003,0.002188088,0.001235698,0.002493931],"category_scores_gemma":[0.01710568,0.001096054,0.001340169,0.0009599448,0.002442168,0.001973311,0.001854769,0.002390689,0.0005152421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001761459,"about_ca_system_score_gemma":0.001219197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01247104,"about_ca_topic_score_gemma":0.01508635,"domain_scores_codex":[0.999141,0.0004362515,0.00003087811,0.000154274,0.0001643098,0.00007321822],"domain_scores_gemma":[0.9880869,0.009386797,0.0007282878,0.0008885384,0.0004844998,0.0004250166],"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":[0.0001005024,0.00004375428,0.004613668,0.00004603611,0.0000784687,0.0001002777,0.0001060786,0.9465351,0.0009953829,0.03573086,0.000769679,0.01088028],"study_design_scores_gemma":[0.000009170886,0.000005536581,0.0003815408,0.000005286419,0.000004130143,0.000008250465,0.00000548311,0.98665,0.0002069309,0.0126242,0.00009285164,0.000006581734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1365516,0.0001948077,0.8603755,0.0004021587,0.00003105461,0.00007842837,0.000388731,0.0007827194,0.001194897],"genre_scores_gemma":[0.8886752,0.0002544581,0.1062566,0.0001786807,0.00009547539,0.0001316384,0.002126623,0.0002345318,0.002046837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01247104,"threshold_uncertainty_score":0.0247969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01990795502176484,"score_gpt":0.2356709707662986,"score_spread":0.2157630157445338,"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."}}