{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.000675681,0.0007353229,0.000641126,0.0011575,0.0004360926,0.001045372,0.005521765,0.0002677087,0.00004649772],"category_scores_gemma":[0.00005559261,0.0006251734,0.0001046698,0.001018696,0.001013855,0.0009614403,0.003602824,0.001313695,0.0001368443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006864566,"about_ca_system_score_gemma":0.0002840353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002298064,"about_ca_topic_score_gemma":0.00005835374,"domain_scores_codex":[0.993881,0.00004456852,0.0005360867,0.00209842,0.002171846,0.001268095],"domain_scores_gemma":[0.9963836,0.0004473076,0.0002752292,0.002260201,0.0003142479,0.000319396],"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":[0.00001191772,0.00005140138,0.00004089017,0.0000634349,0.0000219128,0.0005578496,0.0007852809,0.2799994,0.00005079683,0.002554089,0.00002132908,0.7158417],"study_design_scores_gemma":[0.0006014543,0.0004453059,0.00006958602,0.0006761629,0.000005843075,0.0002709548,2.486957e-7,0.9817252,0.000550488,0.0115433,0.003146341,0.0009650805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006084202,0.0002836599,0.9902265,0.0005436329,0.0009072396,0.0005698201,0.000003906905,0.0002985006,0.007105886],"genre_scores_gemma":[0.05660048,0.00007649196,0.9382753,0.0008555076,0.0004166771,0.00003097398,0.000004073889,0.0001053661,0.003635116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7148766,"threshold_uncertainty_score":0.9999917,"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."}}