{"id":"W4406352735","doi":"10.5195/jmla.2025.1972","title":"Filtering failure: the impact of automated indexing in Medline on retrieval of human studies for knowledge synthesis","year":2025,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Search engine indexing; Information retrieval; MEDLINE; Computer science; Data science; Biology","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"],"consensus_categories":[],"category_scores_codex":[0.001218273,0.00007963356,0.0003021619,0.00007757952,0.00005347822,0.000008045383,0.0003748808,0.0002005224,0.00001121485],"category_scores_gemma":[0.01253603,0.00003950554,0.0002470784,0.0002388289,0.0001106917,0.000007354978,0.0001389965,0.000206034,8.943973e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004837344,"about_ca_system_score_gemma":0.0002517909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001850926,"about_ca_topic_score_gemma":0.000003180805,"domain_scores_codex":[0.9987509,0.000263506,0.000531537,0.00007463407,0.0002625,0.0001168813],"domain_scores_gemma":[0.9980761,0.001096706,0.0005817218,0.0001162908,0.00009508443,0.0000341171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002812142,0.001756315,0.2213235,0.0008293823,0.006659274,0.00001320697,0.00286088,0.0004977288,0.3356752,0.0008417334,0.3940542,0.0326764],"study_design_scores_gemma":[0.004722948,0.002410045,0.2337084,0.004050204,0.0002702498,0.00001468409,0.001906742,0.002825625,0.7360864,0.002935413,0.01076438,0.0003048069],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990914,0.00102761,0.00005115447,0.007454341,0.0002625313,0.00008857575,0.00001617901,0.000007787798,0.0001778392],"genre_scores_gemma":[0.999111,0.0001318001,0.0001691173,0.0001058773,0.0001649927,0.000002487498,0.000002880009,0.000005622921,0.0003062332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4004112,"threshold_uncertainty_score":0.9957818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02149192430396018,"score_gpt":0.3633324058375226,"score_spread":0.3418404815335624,"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."}}