{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002910404,0.00006734239,0.0001564845,0.0005851341,0.0004914781,0.0001437479,0.0007229607,0.00003202125,1.257098e-7],"category_scores_gemma":[0.001885922,0.00004610943,0.00006240267,0.005279626,0.00304052,0.005550937,0.0002995567,0.0001658876,3.148233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528375,"about_ca_system_score_gemma":0.0005275741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003867966,"about_ca_topic_score_gemma":1.687566e-7,"domain_scores_codex":[0.998541,0.00000515893,0.000375114,0.00006044863,0.000727024,0.0002912337],"domain_scores_gemma":[0.9971398,0.0001148698,0.0008110942,0.0001497256,0.001694279,0.00009029871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001409869,0.00005912478,0.02962813,0.0001292143,0.00005224986,1.678135e-7,0.02649892,0.00004195975,0.08885033,0.1932796,0.001717275,0.6597289],"study_design_scores_gemma":[0.003295839,0.002257912,0.1065973,0.0002160439,0.0001117675,0.003457511,0.1363361,0.2709008,0.4240558,0.002164021,0.05010558,0.0005013483],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9591827,0.00003099646,0.0391951,0.0009811152,0.000252156,0.0001514238,0.000002098451,0.00002316481,0.000181216],"genre_scores_gemma":[0.9588031,0.00003410091,0.04093441,0.0002033499,0.00001461041,0.000003694068,6.034514e-8,0.000001275424,0.00000538557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6592276,"threshold_uncertainty_score":0.9996727,"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."}}