{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002623944,0.00008946928,0.000149439,0.0003540868,0.0004444434,0.00004226189,0.0001237437,0.00004105646,0.00003080431],"category_scores_gemma":[0.0001512933,0.00008632628,0.00001192765,0.0007349403,0.001723036,0.0002580805,0.0001421484,0.0001916734,8.669853e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003136247,"about_ca_system_score_gemma":0.000231078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001267244,"about_ca_topic_score_gemma":0.00001896634,"domain_scores_codex":[0.9992476,0.00001952535,0.0002041636,0.0001881243,0.0001682308,0.0001723997],"domain_scores_gemma":[0.9995028,0.00005372005,0.000105884,0.0001031641,0.0002045109,0.00002995441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000344633,0.00001037778,0.7603223,0.00001153076,0.000007490831,2.918751e-8,0.0001571517,0.0000606268,0.0002328918,0.2373821,0.00004435232,0.001767689],"study_design_scores_gemma":[0.0005160596,0.00007169228,0.8721498,0.00004657515,0.00001684122,0.000003866664,0.001456585,0.05460344,0.002366516,0.0678234,0.0008196168,0.0001255622],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843898,0.0004108768,0.01318224,0.001304707,0.00004930082,0.00008448066,0.000009031976,0.00005825838,0.0005113424],"genre_scores_gemma":[0.9992136,0.00001995842,0.0006069393,0.00001600564,0.00001478228,0.00001162288,0.00001785627,0.000003450848,0.00009578327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1695587,"threshold_uncertainty_score":0.6348598,"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."}}