{"id":"W4415917403","doi":"10.1038/s41598-025-20032-7","title":"Using item response theory as a methodology to impute categorical missing values","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health","keywords":"Missing data; Categorical variable; Imputation (statistics); Probabilistic logic; Item response theory; Statistical model; Regression; Binary data","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":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.147193,0.000237043,0.000634364,0.002788198,0.0008702037,0.001370958,0.0009482302,0.000167751,0.000265027],"category_scores_gemma":[0.5818228,0.0001728543,0.0002462322,0.01034443,0.0004109551,0.0002542941,0.0007507223,0.000248422,0.00007229559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000153866,"about_ca_system_score_gemma":0.0008004112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005934123,"about_ca_topic_score_gemma":0.00000188123,"domain_scores_codex":[0.9859491,0.007463156,0.001821782,0.002226457,0.001767397,0.0007721217],"domain_scores_gemma":[0.8744391,0.1196148,0.0009937822,0.003366285,0.001132564,0.0004534815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001104239,0.0001519312,0.02349422,0.00002095513,0.00009751275,0.00260217,0.003778415,0.001655692,0.2453219,0.01433375,0.06729054,0.6401487],"study_design_scores_gemma":[0.00008994747,0.00004857475,0.007517179,0.0000339778,0.00002528885,0.0006998694,0.0009859066,0.001292542,0.01032087,0.9152728,0.06350813,0.0002049242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5205033,0.0003700167,0.4563326,0.001020205,0.01684639,0.0002328335,6.140507e-7,0.0001030781,0.004590913],"genre_scores_gemma":[0.5237219,0.00000115535,0.4459297,0.0007482274,0.0001252487,0.00001226769,0.000001372404,0.00001824256,0.02944191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.900939,"threshold_uncertainty_score":0.9996657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5962277551925372,"score_gpt":0.5607249096711437,"score_spread":0.03550284552139349,"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."}}