{"id":"W4387345643","doi":"10.1093/mnras/stad2997","title":"Marginal post-processing of Bayesian inference products with normalizing flows and kernel density estimators","year":2023,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Radio Astronomy Observations and Technology","field":"Physics and Astronomy","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Science and Technology Facilities Council; Vetenskapsrådet; Kavli Foundation","keywords":"Marginal likelihood; Physics; Cosmic microwave background; Estimator; Bayesian probability; Frequentist inference; Marginal model; Bayesian inference; Dark energy; Statistical physics; Univariate; Cosmology; Statistics; Computer science; Machine learning; Multivariate statistics; Astrophysics; Mathematics; Optics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001597488,0.0001696356,0.0002847119,0.0000253574,0.0001803534,0.00003038751,0.0002930103,0.0000513388,0.00001720619],"category_scores_gemma":[0.0000130324,0.000123445,0.0001116567,0.0002306067,0.0003084907,0.0001416004,0.0002261092,0.0002004668,0.000001649248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002049051,"about_ca_system_score_gemma":0.0001080746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006538374,"about_ca_topic_score_gemma":0.00002215741,"domain_scores_codex":[0.9990038,0.00002417119,0.0002768372,0.0002669879,0.0001233611,0.0003048394],"domain_scores_gemma":[0.999243,0.00006024917,0.0002690313,0.0002655193,0.0001052356,0.00005695921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002337316,0.00005438715,0.7453948,0.00004903521,0.00008437708,6.427146e-8,0.0002334684,0.2477113,0.0001102401,0.0003800666,0.00006176159,0.005897088],"study_design_scores_gemma":[0.000307554,0.0000560613,0.5301592,0.00005170065,0.0000575769,1.416642e-8,0.0007189735,0.4666753,0.001747718,0.00004943912,0.00006030966,0.0001160786],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.997485,0.00001992955,0.001504527,0.0006012462,0.00003974293,0.0001757254,0.00003901549,0.00003541053,0.0000994021],"genre_scores_gemma":[0.9790885,3.668978e-8,0.02077073,0.000006688005,0.00005494264,0.00001135193,0.00001724881,0.00001441475,0.00003601755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.218964,"threshold_uncertainty_score":0.5033942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007772693803403981,"score_gpt":0.2073924196122691,"score_spread":0.1996197258088651,"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."}}