{"id":"W2133411495","doi":"10.1109/ideas.2007.11","title":"An Approach for Text Categorization in Digital Library","year":2007,"lang":"en","type":"article","venue":"International Database Engineering and Applications Symposium","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Categorization; Computer science; Hierarchy; Digital library; Text categorization; Information retrieval; Library classification; Document classification; Artificial intelligence; Data mining; Machine learning; World Wide Web","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":[0.0001130419,0.00008573445,0.00005871085,0.000258551,0.00004111525,0.000262172,0.0005206167,0.00004125093,0.000001648191],"category_scores_gemma":[0.00001480565,0.0000892024,0.00001558142,0.0002625315,0.00001735101,0.001564745,0.00009559481,0.00006350965,0.000003869799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002348496,"about_ca_system_score_gemma":0.00001318062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002228113,"about_ca_topic_score_gemma":2.446333e-7,"domain_scores_codex":[0.9993052,0.000001654693,0.0001858914,0.0002829687,0.00009790323,0.0001263781],"domain_scores_gemma":[0.9995116,0.00006580027,0.00004144697,0.0003010148,0.00003150724,0.0000486375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005333512,0.000162907,0.001458547,0.00002133024,0.00000787511,5.790218e-7,0.00004646451,0.002808837,0.009134793,0.9589514,0.0001917352,0.02721024],"study_design_scores_gemma":[0.0005023284,0.00003207675,0.00283415,0.00001490754,0.000003724901,0.00001454916,0.00008940273,0.8675342,0.0114822,0.003568416,0.1135812,0.0003429292],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001785255,0.0000404762,0.996079,0.0004683434,0.0000587119,0.0002576402,0.000114468,0.0003880204,0.0008080692],"genre_scores_gemma":[0.8698094,0.00004340598,0.1280462,0.00004032454,0.0001094918,0.0003135443,0.001494037,0.0000122063,0.0001313657],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9553829,"threshold_uncertainty_score":0.3637568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007484145434688436,"score_gpt":0.2315351532848341,"score_spread":0.2240510078501457,"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."}}