{"id":"W1546703457","doi":"10.1137/1.9781611972733.6","title":"Hierarchical Document Clustering Using Frequent Itemsets","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":469,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Information retrieval; Hierarchical clustering; Brown clustering; Intuition; Vocabulary; Artificial intelligence; Library science; Fuzzy clustering; Canopy clustering algorithm; Psychology","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":[0.0001655708,0.00007049591,0.00006650003,0.00003925569,0.0001280346,0.000194262,0.0003785386,0.00002186805,0.000049464],"category_scores_gemma":[0.00001782131,0.00006135506,0.00002153374,0.0002212609,0.00001783936,0.0002684695,0.0001536759,0.00006676271,0.0000536338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003668044,"about_ca_system_score_gemma":0.00003833855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005386897,"about_ca_topic_score_gemma":0.000003453727,"domain_scores_codex":[0.9992689,0.0000261975,0.0001352514,0.0002503507,0.0001347805,0.0001845063],"domain_scores_gemma":[0.9994065,0.00002825223,0.00002592759,0.0004292092,0.00002249823,0.0000876153],"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":[2.81391e-7,0.00007717373,0.0002419164,0.000006891718,0.00001433423,0.00001149882,0.0002826278,0.0006000337,0.00238543,0.8996252,0.001073237,0.09568136],"study_design_scores_gemma":[0.000487368,0.00005517537,0.0007746704,0.00003476788,0.000008476417,0.0002176527,0.00005808955,0.8474373,0.007602897,0.01820283,0.1245848,0.0005359126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008140318,0.00001888097,0.9842293,0.0003759536,0.0001372207,0.00006850819,0.000001330982,0.0001054858,0.006923061],"genre_scores_gemma":[0.1496608,0.000003740232,0.8496949,0.000309472,0.00002389492,0.000008290268,0.000002192223,0.000005043441,0.0002915945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8814224,"threshold_uncertainty_score":0.2501987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03053123436791092,"score_gpt":0.2888526014938362,"score_spread":0.2583213671259252,"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."}}