{"id":"W2145753452","doi":"10.1109/ccece.2007.203","title":"Document Classification with ACM Subject Hierarchy","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Categorization; Information retrieval; Hierarchy; Classifier (UML); Document classification; Text categorization; Digital library; Classification scheme; Library classification; Subject (documents); Focus (optics); Context (archaeology); Artificial intelligence; World Wide Web; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004227419,0.0001109996,0.00008608412,0.0001995657,0.0001077429,0.0001790794,0.00133436,0.00005969958,0.00004681128],"category_scores_gemma":[0.00005577844,0.0000780409,0.00002672451,0.0006036595,0.00007836929,0.0006270581,0.0002187709,0.0001032038,0.0001652172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007554482,"about_ca_system_score_gemma":0.00004169421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001232461,"about_ca_topic_score_gemma":0.00002457681,"domain_scores_codex":[0.9988625,0.00001488484,0.0001988449,0.0003469696,0.0003021625,0.0002746595],"domain_scores_gemma":[0.9984389,0.0001095731,0.00008554925,0.001232688,0.00006981637,0.00006348244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00000920359,0.00003452636,0.003379921,0.000002686209,0.000007686695,0.000004047205,0.0001125309,8.726059e-7,0.002353747,0.8079497,0.001729022,0.184416],"study_design_scores_gemma":[0.001612626,0.000773238,0.3570632,0.0000303727,0.00001531182,0.00005823516,0.001378039,0.001814129,0.2518701,0.1894144,0.1949099,0.001060419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0251084,0.0000364308,0.9364747,0.009163386,0.0000947539,0.000184263,1.580558e-7,0.001317331,0.02762055],"genre_scores_gemma":[0.8392577,0.00001376236,0.1581962,0.0002355295,0.00001692299,0.0000171434,0.000002011021,0.000005023779,0.002255698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8141493,"threshold_uncertainty_score":0.3182416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711306376552129,"score_gpt":0.2802209110725788,"score_spread":0.2531078473070575,"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."}}