{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","open_science"],"category_scores_codex":[0.07053809,0.0002700201,0.0005533012,0.1563281,0.003936335,0.007741136,0.00913916,0.00008013238,0.00123926],"category_scores_gemma":[0.04453339,0.0001722012,0.0003984683,0.677848,0.002063906,0.002198376,0.008683388,0.0007412321,0.00003854296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002937267,"about_ca_system_score_gemma":0.0007736293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002183983,"about_ca_topic_score_gemma":0.00002565573,"domain_scores_codex":[0.9656685,0.0009097184,0.001389725,0.001500527,0.02924583,0.001285721],"domain_scores_gemma":[0.984528,0.007917204,0.001127053,0.002313303,0.003379766,0.000734643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003080066,0.0003192126,0.9601827,0.00001629215,0.00002167997,0.00001314291,0.0005438753,0.003569396,0.002077784,0.00122936,0.01254601,0.01944974],"study_design_scores_gemma":[0.0009178443,0.0002693451,0.7697348,0.00002549006,0.00003962694,0.00003573169,0.003192758,0.1297799,0.01090223,0.007883293,0.07650656,0.0007124588],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879879,0.00150755,0.001336118,0.0005236595,0.005355228,0.0005331596,0.0002966055,0.00005249959,0.002407278],"genre_scores_gemma":[0.9935462,0.00003578988,0.0008749705,0.00005438668,0.00008843888,0.00002352016,0.0000130533,0.00002798866,0.005335636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.52152,"threshold_uncertainty_score":0.9996737,"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."}}