{"id":"W2036179015","doi":"10.1002/asi.22749","title":"Constructing a true<scp>LCSH</scp>tree of a science and engineering collection","year":2012,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Interdisciplinary Research in Music Media and Technology; McGill University","funders":"McGill University","keywords":"Subject (documents); Computer science; Tree structure; Tree (set theory); Domain (mathematical analysis); Information retrieval; Controlled vocabulary; Process (computing); Data collection; World Wide Web; Data structure; Mathematics; Statistics; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["scholarly_communication"],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["scholarly_communication"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009097435,0.0002098351,0.0003200632,0.004303313,0.001782345,0.002570416,0.0007439553,0.0007041311,0.004667216],"category_scores_gemma":[0.007543874,0.0005012259,0.0006680392,0.005547996,0.0009583223,0.0026168,0.001258509,0.0008471439,0.002326158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001331921,"about_ca_system_score_gemma":0.002395966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01464694,"about_ca_topic_score_gemma":0.02491185,"domain_scores_codex":[0.9990553,0.0001883107,0.00005762215,0.0001172402,0.0004790791,0.0001023767],"domain_scores_gemma":[0.9962741,0.00120514,0.0003128722,0.0006271444,0.001407026,0.0001737226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000400846,0.0002918644,0.05806456,0.001508897,0.0001180929,0.003142189,0.009703587,0.02330784,0.04493408,0.2455615,0.09754525,0.5154213],"study_design_scores_gemma":[0.0000545048,0.0002039007,0.05933076,0.0004332568,0.00012642,0.002581846,0.004984714,0.3020355,0.02837456,0.1910605,0.4106125,0.0002015745],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1734382,0.0005554853,0.7406401,0.002296538,0.0001574343,0.0009682686,0.02072032,0.006778399,0.05444527],"genre_scores_gemma":[0.2476001,0.0004155501,0.7147394,0.0002605134,0.00005035364,0.0003111929,0.02575026,0.00135862,0.009513988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9974296,"threshold_uncertainty_score":0.02912337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01094168810940199,"score_gpt":0.2545057719737588,"score_spread":0.2435640838643568,"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."}}