{"id":"W2147840212","doi":"10.1007/978-3-540-39935-3_22","title":"Enhanced phrase-based document clustering using Self-Organizing Map (SOM) architectures","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Self-organizing map; Phrase; Cluster analysis; Computer science; Artificial intelligence; Natural language processing; Document clustering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003685013,0.0005144289,0.0006789834,0.0002678988,0.0005657569,0.0002341699,0.0006630064,0.000137204,0.000003529755],"category_scores_gemma":[0.00003541727,0.0004959062,0.00008577981,0.0001526014,0.0001556153,0.0001044322,0.0015642,0.0004381567,0.000005433166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002732593,"about_ca_system_score_gemma":0.0001414478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003722128,"about_ca_topic_score_gemma":0.00003327158,"domain_scores_codex":[0.9976394,0.00002479857,0.0006020505,0.0009452434,0.0003165696,0.0004718979],"domain_scores_gemma":[0.9986235,0.0002480602,0.0003384709,0.0005691259,0.0001350012,0.00008579593],"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":[0.00002957636,0.0002286484,0.0001589961,0.004776671,0.001092841,0.0004011921,0.03208149,0.1383475,0.0006507735,0.1410943,0.0001969239,0.6809411],"study_design_scores_gemma":[0.004295698,0.0002991369,0.0003021021,0.01690727,0.0002933094,0.0001182157,0.001323025,0.8745294,0.0007826212,0.08930733,0.007054767,0.004787146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005721544,0.005346478,0.9820125,0.0003934525,0.001261632,0.0006378395,0.00001813775,0.0005396149,0.004068847],"genre_scores_gemma":[0.4526298,0.0002957851,0.5447866,0.0004394641,0.0008037572,0.00002665452,0.00002417153,0.0001193316,0.0008744097],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7361819,"threshold_uncertainty_score":0.9997492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03531482692826102,"score_gpt":0.2978583838462532,"score_spread":0.2625435569179921,"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."}}