{"id":"W2141870796","doi":"10.5539/cis.v6n3p89","title":"Clustering of Web Search Results Based on Document Segmentation","year":2013,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Information retrieval; Data mining; Similarity (geometry); Brown clustering; Segmentation; Fuzzy clustering; Correlation clustering; Search engine; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002107654,0.0008456829,0.001608865,0.008912053,0.001088087,0.00198928,0.000874446,0.0009544447,0.000638651],"category_scores_gemma":[0.008555495,0.0004351415,0.0009022789,0.006798681,0.0007919506,0.001505131,0.0008082977,0.0004762307,0.0006555766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293751,"about_ca_system_score_gemma":0.001151567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0098913,"about_ca_topic_score_gemma":0.009555783,"domain_scores_codex":[0.9978026,0.0005522038,0.0002218362,0.0003778927,0.000858725,0.000186867],"domain_scores_gemma":[0.9944901,0.001776743,0.0007276607,0.0006168422,0.002218256,0.0001703951],"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":[0.002635964,0.0005122033,0.03037636,0.001093345,0.0006717912,0.0003815706,0.002063988,0.2205531,0.08963668,0.004340783,0.007914179,0.63982],"study_design_scores_gemma":[0.0001076308,0.0004980227,0.03594643,0.00009656137,0.0002725745,0.0004619798,0.0009967076,0.8965944,0.05389601,0.007182532,0.003791603,0.0001555462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4855112,0.002667201,0.5020093,0.0002317417,0.00008484702,0.0008476316,0.001077297,0.003642603,0.003928004],"genre_scores_gemma":[0.649484,0.0005329428,0.3443775,0.00005414823,0.00005346535,0.0002773136,0.003189844,0.000337504,0.001693206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0098913,"threshold_uncertainty_score":0.01966745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01516549125906185,"score_gpt":0.2615319963349998,"score_spread":0.246366505075938,"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."}}