{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00470261,0.0009005273,0.00106864,0.1504222,0.001575557,0.009952385,0.0006598224,0.0008472997,0.01712294],"category_scores_gemma":[0.038123,0.0002990892,0.001342733,0.177445,0.000619357,0.005432299,0.002954598,0.0006422146,0.005007069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001926933,"about_ca_system_score_gemma":0.0077847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02107375,"about_ca_topic_score_gemma":0.01630556,"domain_scores_codex":[0.9934296,0.001699433,0.001591328,0.0007661849,0.002154926,0.000358648],"domain_scores_gemma":[0.9709598,0.01334053,0.00643629,0.00248615,0.005956321,0.0008209745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002814996,0.000150348,0.1124126,0.009709301,0.001053354,0.0003867369,0.004901415,0.002080046,0.006517496,0.05238573,0.05878003,0.7513415],"study_design_scores_gemma":[0.00008939498,0.0002588963,0.1764528,0.002488328,0.001128144,0.0006480978,0.01063823,0.005161469,0.01057192,0.03920665,0.7532001,0.0001559885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3209675,0.04473681,0.07737941,0.005057373,0.002571298,0.001362219,0.2956401,0.00591564,0.2463696],"genre_scores_gemma":[0.6428392,0.03223612,0.1674922,0.0006780432,0.001533253,0.001932261,0.1287274,0.000712313,0.02384918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8495778,"threshold_uncertainty_score":0.05728191,"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."}}