{"id":"W2001738847","doi":"10.5539/mas.v3n9p72","title":"A New Method of Hierarchical Text Clustering Based on Lsa-Hgsom","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Brown clustering; Correlation clustering; Latent semantic analysis; Data mining; Single-linkage clustering; Artificial intelligence; Clustering high-dimensional data; CURE data clustering algorithm; Vector space model; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003753361,0.0001240627,0.0001494473,0.0001962965,0.0002022847,0.00008571915,0.001472494,0.00003420425,0.000004170057],"category_scores_gemma":[0.00001732982,0.0001171085,0.00004426794,0.001052926,0.0001041478,0.0001926081,0.0001660108,0.0001445572,0.000009352626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005660142,"about_ca_system_score_gemma":0.0002470389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003393762,"about_ca_topic_score_gemma":7.423983e-7,"domain_scores_codex":[0.9982874,0.00001315394,0.0002241413,0.0005852178,0.0006063096,0.0002837094],"domain_scores_gemma":[0.9989128,0.0001201898,0.00009955379,0.0006417304,0.00006186284,0.0001638226],"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":[0.00000685455,0.00004556547,9.450732e-7,0.000001660781,4.791455e-7,5.354369e-7,0.0001048786,0.1014502,0.1091926,0.363014,0.00003750794,0.4261448],"study_design_scores_gemma":[0.000122451,0.0000569216,0.0002584553,0.000008088632,8.381542e-7,0.000002408906,0.000001151035,0.7163587,0.01546624,0.2673835,0.0002458752,0.00009535324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008971561,0.000003889678,0.9853092,0.001978329,0.00002201874,0.0002129234,0.000001039904,0.0001972938,0.01218559],"genre_scores_gemma":[0.4718941,3.722792e-7,0.5272365,0.0008156671,0.00001406324,0.000009964179,3.794109e-7,0.00000276935,0.00002619371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6149085,"threshold_uncertainty_score":0.4775546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02084772498625357,"score_gpt":0.3289332041387431,"score_spread":0.3080854791524895,"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."}}