{"id":"W4410397499","doi":"10.1016/j.sapharm.2025.05.008","title":"Consistency of Medical Subject Headings assignment: A test-retest reliability analysis","year":2025,"lang":"en","type":"article","venue":"Research in Social and Administrative Pharmacy","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Subject (documents); Reliability (semiconductor); Test (biology); Information retrieval; Computer science; Psychology; Reliability engineering; Artificial intelligence; World Wide Web; Engineering; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1573945,0.001071005,0.003034658,0.009546117,0.001667236,0.003317579,0.001615906,0.001205915,0.00183542],"category_scores_gemma":[0.3533142,0.0008955316,0.005186541,0.006901566,0.00281239,0.003316449,0.004376858,0.001326661,0.0009663721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001732808,"about_ca_system_score_gemma":0.002578802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001583067,"about_ca_topic_score_gemma":0.002691925,"domain_scores_codex":[0.814525,0.08559629,0.04317192,0.01788214,0.03698185,0.001842742],"domain_scores_gemma":[0.5374326,0.2768863,0.04360219,0.03091369,0.1096916,0.001473777],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009013396,0.001040454,0.6792457,0.01517059,0.01634644,0.000425511,0.03382018,0.00343681,0.01386855,0.004308515,0.0110561,0.2122677],"study_design_scores_gemma":[0.001877196,0.005699174,0.8664946,0.004931121,0.01038206,0.001275712,0.009154501,0.02276166,0.02218161,0.01169601,0.04274472,0.0008016068],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7985722,0.01192886,0.1418778,0.00125422,0.002442899,0.02185469,0.005908611,0.001339733,0.01482097],"genre_scores_gemma":[0.8977398,0.001237869,0.07900105,0.0003455039,0.0003568075,0.01629861,0.002882028,0.0003969287,0.001741361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8426055,"threshold_uncertainty_score":0.8323916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1753936504615749,"score_gpt":0.5228577643158194,"score_spread":0.3474641138542446,"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."}}