{"id":"W4413484588","doi":"10.1101/2025.08.21.25334182","title":"A Simulation Study to Advance Human-Centred Artificial Intelligence via Digital Citizen Science: Can Large Language Models Transform Current Approaches to Missing Data Imputation?","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Imputation (statistics); Missing data; Computer science; Artificial intelligence; Data science; Current (fluid); Machine learning; Data mining; Engineering; Electrical engineering","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":[0.00253588,0.0002874889,0.0004187003,0.000599928,0.001067103,0.0008251368,0.001708779,0.00007000011,0.00002741888],"category_scores_gemma":[0.0009100466,0.0002934813,0.0001142578,0.001847254,0.0001611482,0.0005251474,0.00112657,0.0003313292,0.000009499702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003192492,"about_ca_system_score_gemma":0.0008394603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000625851,"about_ca_topic_score_gemma":0.003542477,"domain_scores_codex":[0.9959596,0.0002908687,0.0006681854,0.001250973,0.001302259,0.0005281275],"domain_scores_gemma":[0.998071,0.000410288,0.0001788518,0.000699834,0.0003138157,0.0003262472],"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":[0.00001578076,0.0004526104,0.0005455489,0.00003060025,0.00003275883,0.000002663954,0.08202249,0.5081363,0.0000076662,0.006042604,0.000002773131,0.4027082],"study_design_scores_gemma":[0.0000798898,0.00003473404,0.0006502101,0.000111722,0.0001008826,7.996977e-8,0.01771159,0.8402478,0.00005229764,0.1402915,0.0002844216,0.0004349352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1413868,0.0001830874,0.8536378,0.001214361,0.0004684117,0.001537321,0.0003262697,0.0001120382,0.00113397],"genre_scores_gemma":[0.9920616,0.000002761671,0.007100935,0.00004609396,0.0003064883,0.0000484482,0.0002799343,0.00001343668,0.0001402795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8506748,"threshold_uncertainty_score":0.9999517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2879845659338913,"score_gpt":0.4615149857511824,"score_spread":0.1735304198172911,"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."}}