{"id":"W1568806324","doi":"10.1007/3-540-45683-x_46","title":"Efficiently Clustering Documents with Committees","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Similarity (geometry); Set (abstract data type); Data mining; Task (project management); Group (periodic table); Cluster (spacecraft); Space (punctuation); Document clustering; Correlation clustering; Single-linkage clustering; CURE data clustering algorithm; Information retrieval; Artificial intelligence; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002685708,0.001715327,0.002724117,0.003789158,0.001945948,0.003155647,0.003063902,0.001808059,0.006868679],"category_scores_gemma":[0.009371942,0.001578263,0.00234279,0.006356691,0.0008368842,0.003729537,0.003381313,0.002091709,0.008401155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009673389,"about_ca_system_score_gemma":0.001842824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002927897,"about_ca_topic_score_gemma":0.006508689,"domain_scores_codex":[0.9963154,0.00127547,0.0002879675,0.0007203926,0.001156794,0.0002438877],"domain_scores_gemma":[0.9955687,0.001431274,0.0002168973,0.001539301,0.001028623,0.0002152077],"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":[0.0006312073,0.0002295832,0.0009432637,0.0003383723,0.000244606,0.0001053726,0.000165689,0.04881746,0.01805681,0.01251808,0.04411806,0.8738315],"study_design_scores_gemma":[0.0001758055,0.0002090296,0.0008533716,0.00005898819,0.0001773566,0.0004228434,0.0001566139,0.8676834,0.03053365,0.07318313,0.02648251,0.00006330356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01048086,0.0008877034,0.9777827,0.0002442684,0.000130656,0.0002088496,0.0006933438,0.006488958,0.00308279],"genre_scores_gemma":[0.06185454,0.0005124663,0.9210721,0.0001563673,0.0002129873,0.000281065,0.00489845,0.000935293,0.01007676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006868679,"threshold_uncertainty_score":0.02297807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01851931358767292,"score_gpt":0.269153790340296,"score_spread":0.2506344767526231,"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."}}