{"id":"W4416780419","doi":"10.1109/bigdata66926.2025.11401828","title":"Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation","year":2025,"lang":"","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Missing data; Imputation (statistics); Calibration; Reliability (semiconductor); Empirical likelihood; Empirical research; Observational error; Measurement uncertainty","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002935972,0.000720898,0.001200545,0.001200025,0.000221892,0.000365717,0.002829667,0.0005970256,0.0001101558],"category_scores_gemma":[0.002304192,0.0007520946,0.0001713454,0.002133227,0.0001282865,0.001477259,0.004286194,0.002043762,0.00001111766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005943265,"about_ca_system_score_gemma":0.001453202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005106072,"about_ca_topic_score_gemma":0.001572972,"domain_scores_codex":[0.9914408,0.002335228,0.002288697,0.002128755,0.001226631,0.0005798738],"domain_scores_gemma":[0.9940267,0.001812007,0.001396137,0.001986284,0.0006070201,0.0001718168],"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":[0.00009387059,0.001640604,0.02336488,0.0001498486,0.00005956037,0.00001477524,0.03481334,0.7934095,0.000004559099,0.001680008,0.00001379419,0.1447553],"study_design_scores_gemma":[0.00177648,0.0007339987,0.06104967,0.0002083318,0.00007921949,0.000002521845,0.003755598,0.9125693,0.00001542613,0.01926726,0.000006155851,0.0005360663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3708043,0.00001480772,0.6245879,0.000522765,0.001179371,0.001589734,0.000004707739,0.000110349,0.001186098],"genre_scores_gemma":[0.8927961,0.000007370856,0.1066957,0.0001296878,0.0000748864,0.00008554185,0.0000606608,0.00001896697,0.00013107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5219918,"threshold_uncertainty_score":0.999493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0324590033592787,"score_gpt":0.3851021096578575,"score_spread":0.3526431062985788,"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."}}