{"id":"W2762227057","doi":"10.1016/j.joi.2017.08.008","title":"Mapping science using Library of Congress Subject Headings","year":2017,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Subject (documents); Library of congress; Computer science; Information retrieval; Library science; Library of Congress Classification; Data science; Library classification","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","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.03637953,0.0001379398,0.0005627316,0.1587591,0.0008683075,0.006599371,0.008046128,0.0001025527,0.0001613242],"category_scores_gemma":[0.1688239,0.00009046518,0.0002891535,0.1815109,0.001071635,0.009738696,0.001619573,0.0004331194,0.00001938649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001480388,"about_ca_system_score_gemma":0.001854447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003830651,"about_ca_topic_score_gemma":6.147794e-7,"domain_scores_codex":[0.9847053,0.00004818306,0.001806636,0.0002514006,0.01260264,0.0005858891],"domain_scores_gemma":[0.9825504,0.003134933,0.004444747,0.001009158,0.008259776,0.0006010294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005551989,0.00009712867,0.7317294,0.00002332576,0.00002748404,0.00005314564,0.0002860258,0.0001249723,0.006250595,0.0008795857,0.005254867,0.2552179],"study_design_scores_gemma":[0.001936571,0.0008718615,0.834496,0.0002224373,0.00001910701,0.0004167346,0.002046639,0.01935209,0.06793457,0.006584588,0.06565077,0.0004686899],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748696,0.0005421247,0.004421067,0.0002423976,0.002062415,0.00009437589,0.00001497476,0.00000447283,0.01774855],"genre_scores_gemma":[0.9868807,0.0005386416,0.011858,0.00006332413,0.0001376715,1.70406e-7,1.526588e-7,0.000008588626,0.0005128154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2547492,"threshold_uncertainty_score":0.9973208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6384368990329121,"score_gpt":0.5833211230820153,"score_spread":0.05511577595089678,"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."}}