{"id":"W4234033320","doi":"10.1145/564410.564412","title":"Document clustering with committees","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Similarity (geometry); Set (abstract data type); Information retrieval; Task (project management); Data mining; Fuzzy clustering; Space (punctuation); Group (periodic table); Cluster (spacecraft); 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":[0.01134114,0.001508755,0.001863919,0.005260872,0.001899027,0.004119373,0.002381023,0.002059791,0.006072144],"category_scores_gemma":[0.04294548,0.0008841383,0.002259077,0.007452406,0.001203964,0.004288554,0.00310279,0.002026156,0.004962713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001236762,"about_ca_system_score_gemma":0.001686919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002346062,"about_ca_topic_score_gemma":0.00229154,"domain_scores_codex":[0.9833065,0.00845807,0.00144728,0.002613508,0.003714978,0.0004596161],"domain_scores_gemma":[0.9788476,0.008628575,0.001258181,0.005768776,0.005040655,0.0004563541],"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":[0.0006000848,0.0001613644,0.002381474,0.0006352631,0.0004224931,0.0001233209,0.0005694666,0.123865,0.005651653,0.05854049,0.03026434,0.776785],"study_design_scores_gemma":[0.0001723019,0.0003751784,0.001789092,0.0001363772,0.0002151914,0.0005560393,0.0002490046,0.7769753,0.01947154,0.1285168,0.07142216,0.0001210809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0046055,0.0005955616,0.987379,0.0001459978,0.0001174009,0.0003880141,0.0004526863,0.002574588,0.003741291],"genre_scores_gemma":[0.06968011,0.0004716022,0.9204945,0.0001546121,0.0002491134,0.0007264272,0.002411116,0.0007596722,0.00505278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01134114,"threshold_uncertainty_score":0.05997843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517323618068653,"score_gpt":0.3218864163618488,"score_spread":0.2567131801811622,"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."}}