{"id":"W4416163443","doi":"10.1088/2632-2153/ae1f05","title":"Towards instance-wise calibration: local amortized diagnostics and reshaping of conditional densities (LADaR)","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; U.S. Department of Energy; Office of Science; Division of Mathematical Sciences; National Science Foundation","keywords":"Python (programming language); Probabilistic logic; Benchmark (surveying); Probability density function; Conditional probability distribution; Calibration; Key (lock); Density estimation; Feature (linguistics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007335517,0.001586606,0.001797579,0.001775609,0.000885491,0.002700162,0.005235639,0.002682573,0.003510784],"category_scores_gemma":[0.03546754,0.001165027,0.002008181,0.00143674,0.002307201,0.004702926,0.004790472,0.006683344,0.001510285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001961418,"about_ca_system_score_gemma":0.002210944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006806352,"about_ca_topic_score_gemma":0.00637931,"domain_scores_codex":[0.9973559,0.001212897,0.0001280249,0.0006867027,0.0004254504,0.0001910016],"domain_scores_gemma":[0.9852841,0.008180233,0.001176646,0.003628522,0.001277689,0.0004526842],"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":[0.0003397038,0.0001798308,0.009369444,0.0002106732,0.0002790583,0.0002216818,0.0003943265,0.6793955,0.003912338,0.05881738,0.0141875,0.2326925],"study_design_scores_gemma":[0.00001873664,0.00001826103,0.0003995125,0.00001849738,0.00001237766,0.00004588326,0.00002269225,0.9670436,0.001346981,0.03011509,0.0009401567,0.00001830975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01616652,0.0002682622,0.9771253,0.000559294,0.00004608232,0.00006921015,0.0002967023,0.004699644,0.000768957],"genre_scores_gemma":[0.3319084,0.0002096557,0.6601813,0.001116517,0.0001919187,0.0002490201,0.00246156,0.001887942,0.001793678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007335517,"threshold_uncertainty_score":0.0387944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004579382784567398,"score_gpt":0.2234420570774178,"score_spread":0.2188626742928504,"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."}}