{"id":"W4408047762","doi":"10.1007/s42081-025-00298-x","title":"Application of machine learning methods in the imputation of heterogeneous co-missing data","year":2025,"lang":"en","type":"article","venue":"Japanese Journal of Statistics and Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"Canadian Institutes of Health Research; McLaughlin Centre, University of Toronto","keywords":"Imputation (statistics); Missing data; Computer science; Machine learning; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.008062416,0.00005570119,0.0001612732,0.0001792061,0.0001044959,0.00008896501,0.002255977,0.00001518639,5.016219e-7],"category_scores_gemma":[0.0009617191,0.00003622057,0.000008056644,0.00065722,0.0002080723,0.0007978548,0.0004907674,0.0001243593,4.524664e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008691977,"about_ca_system_score_gemma":0.0001415471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006220733,"about_ca_topic_score_gemma":0.000005375159,"domain_scores_codex":[0.9986914,0.000245934,0.0004379708,0.0002196851,0.0003031411,0.0001017999],"domain_scores_gemma":[0.9979514,0.0007330042,0.0004063822,0.0006940695,0.000178123,0.00003696814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001257895,0.00004770796,0.001193274,0.00003999022,0.000005997414,0.000004794082,0.001417018,0.0005527546,0.0434262,0.04048116,0.00001743724,0.9128011],"study_design_scores_gemma":[0.0001643556,0.00005995919,0.004483919,0.00002520601,0.00001081494,0.00006559426,0.00008535796,0.9680678,0.001668935,0.02519498,0.0001341198,0.00003901715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005165326,0.0002062857,0.9942375,0.0001894203,0.00003807244,0.00005802934,0.00004517241,0.000001724664,0.0000584975],"genre_scores_gemma":[0.4065149,0.00004232204,0.5933954,0.00003502913,0.000004065112,1.999594e-7,0.000006593714,8.160188e-7,7.24785e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.967515,"threshold_uncertainty_score":0.4192204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04797112399033372,"score_gpt":0.4199266282748576,"score_spread":0.3719555042845239,"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."}}