{"id":"W2064514861","doi":"10.1142/s021848850400317x","title":"TEXTUAL-BASED CLUSTERING OF WEB DOCUMENTS","year":2004,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Information retrieval; Schematic; Fuzzy clustering; Directory; Web page; HTML element; Document clustering; Data mining; Web mining; Feature (linguistics); World Wide Web; Artificial intelligence","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":[0.0008587227,0.0001825961,0.0004184754,0.0005908032,0.00006618179,0.0002632895,0.001175781,0.00006673564,0.00000726595],"category_scores_gemma":[0.000122052,0.0001442172,0.0001921058,0.000343584,0.0000792023,0.0004102509,0.000128263,0.0001502436,0.000006404445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001624369,"about_ca_system_score_gemma":0.0006960692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002420826,"about_ca_topic_score_gemma":0.00007149336,"domain_scores_codex":[0.9980022,0.0001092487,0.0008376091,0.0002342177,0.0006316422,0.0001850622],"domain_scores_gemma":[0.9973879,0.0001857523,0.0007223421,0.0002733962,0.001288369,0.0001422135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003952993,0.001195901,0.007515113,0.0004776679,0.00102368,0.0003104955,0.0008627788,0.9214476,0.01005285,0.01876391,0.0008862702,0.03706837],"study_design_scores_gemma":[0.009160018,0.0005395602,0.0009794362,0.003172815,0.000112122,0.0002004685,0.0006282453,0.9719144,0.002314982,0.0003782424,0.01008195,0.0005177401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1266911,0.001664857,0.8654091,0.001641151,0.002681244,0.0001428709,0.00006395798,0.00004564121,0.001660118],"genre_scores_gemma":[0.9967082,0.0000266385,0.002811951,0.00006814256,0.0002985003,0.000004513412,0.00001057612,0.000009568058,0.00006188741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8700171,"threshold_uncertainty_score":0.5881006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01590388508604498,"score_gpt":0.2784247356577021,"score_spread":0.2625208505716571,"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."}}