{"id":"W4281255308","doi":"10.1007/s11192-022-04387-6","title":"Measuring the disparity among scientific disciplines using Library of Congress Subject Headings","year":2022,"lang":"en","type":"article","venue":"Scientometrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Subject (documents); Library of congress; Computer science; Information retrieval; Bibliometrics; Scientific literature; Library science; Data science; Scientific communication","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00905817,0.000318356,0.0007619849,0.02852808,0.0008269196,0.004264819,0.0004934448,0.0005896189,0.002499592],"category_scores_gemma":[0.08230986,0.000155483,0.0005827675,0.04242875,0.0006127154,0.002641,0.002873915,0.000588459,0.0007223774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001250363,"about_ca_system_score_gemma":0.002409132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009133617,"about_ca_topic_score_gemma":0.006625588,"domain_scores_codex":[0.9883673,0.003091815,0.001757187,0.000964526,0.005124729,0.0006944928],"domain_scores_gemma":[0.9508976,0.02469357,0.01128131,0.003097896,0.008676196,0.00135361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001313486,0.00007891841,0.9460102,0.0001933456,0.0002991887,0.00003719419,0.001497426,0.0004330516,0.001323607,0.003472218,0.001396813,0.04512668],"study_design_scores_gemma":[0.00001835023,0.0001053739,0.9811446,0.00008319585,0.000164863,0.0001170455,0.003835111,0.002010364,0.001557357,0.004525421,0.006410291,0.00002782991],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9791364,0.001340176,0.002874702,0.0004350864,0.00005894063,0.0000745046,0.004571883,0.00006357158,0.01144476],"genre_scores_gemma":[0.9941393,0.0004262534,0.001878164,0.0000615143,0.00008203435,0.0000539666,0.002943174,0.00001205982,0.0004035613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9714719,"threshold_uncertainty_score":0.04790473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6099867867029692,"score_gpt":0.5220149078759858,"score_spread":0.08797187882698343,"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."}}