{"id":"W4383748099","doi":"10.5195/jmla.2023.1588","title":"Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study","year":2023,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; University of British Columbia Hospital; University of British Columbia","funders":"","keywords":"Search engine indexing; MEDLINE; Information retrieval; Computer science; National library; Library science","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","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03359193,0.0002376892,0.0008786577,0.001331203,0.0004264171,0.001255641,0.005535144,0.0004128407,0.001171471],"category_scores_gemma":[0.07895181,0.0001469799,0.0001893536,0.006510706,0.00008199145,0.003409854,0.001934973,0.00270413,0.00007368314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003921048,"about_ca_system_score_gemma":0.001376916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008635284,"about_ca_topic_score_gemma":0.0000723641,"domain_scores_codex":[0.9807469,0.00263246,0.002922664,0.0004190647,0.01267551,0.0006034158],"domain_scores_gemma":[0.9909306,0.00515382,0.002268976,0.0004283552,0.000320967,0.0008973501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008901938,0.000387697,0.8586596,0.000004035338,0.00008282853,0.0001878461,0.001984949,0.001339122,0.00004918757,0.00008151328,0.1353562,0.001777992],"study_design_scores_gemma":[0.003678878,0.0002959831,0.9019398,0.0007163459,0.00003896586,0.00006396153,0.003993273,0.07702304,0.00005997491,0.004873307,0.006977913,0.0003385575],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9533287,0.00003030766,0.0001179694,0.04294226,0.002030628,0.0003188241,0.000007244706,0.0001615135,0.001062531],"genre_scores_gemma":[0.9930305,0.000006158659,0.0001082112,0.004137953,0.001093934,0.000005695302,0.000004001245,0.00003166994,0.001581864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1283783,"threshold_uncertainty_score":0.9998454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1143814894737909,"score_gpt":0.4322647871139451,"score_spread":0.3178832976401542,"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."}}