{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09115881,0.001768654,0.001501243,0.003574743,0.001589258,0.003656065,0.0031267,0.003320245,0.001949974],"category_scores_gemma":[0.4626545,0.001026676,0.001786226,0.004678293,0.006962813,0.01061486,0.004915413,0.005979398,0.0005246701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002489349,"about_ca_system_score_gemma":0.001767041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00269974,"about_ca_topic_score_gemma":0.001719439,"domain_scores_codex":[0.93673,0.04314752,0.002742885,0.006923635,0.009373263,0.001082752],"domain_scores_gemma":[0.2829618,0.6364678,0.01768,0.05080331,0.01100645,0.001080678],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001198963,0.0003092947,0.1502167,0.001428993,0.002018682,0.0003887741,0.002025585,0.5815942,0.002094785,0.09124174,0.008593306,0.158889],"study_design_scores_gemma":[0.0001154085,0.0006025876,0.03378857,0.001033962,0.0004306877,0.001269326,0.0008234295,0.7464978,0.01043605,0.1945905,0.01016237,0.0002492817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1990048,0.01090034,0.7755241,0.004814158,0.0002556596,0.0002579347,0.00172432,0.001499593,0.006019118],"genre_scores_gemma":[0.8861587,0.002024704,0.1065014,0.0007956412,0.0003073949,0.0002566949,0.002289467,0.0008921072,0.0007738372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9088412,"threshold_uncertainty_score":0.4820996,"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."}}