{"id":"W1987149779","doi":"10.1023/b:jiis.0000029668.88665.1a","title":"Interval Set Clustering of Web Users with Rough K-Means","year":2004,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":523,"is_retracted":false,"has_abstract":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Data mining; Web mining; Rough set; Fuzzy clustering; Set (abstract data type); Information retrieval; Machine learning; Web page; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006199573,0.000122654,0.0002844424,0.0002875037,0.00004489234,0.0002330055,0.0006380524,0.00005317991,0.000003780601],"category_scores_gemma":[0.00002691758,0.00008051756,0.0001080817,0.000304437,0.00002799175,0.002735239,0.00007802777,0.0001633056,0.0000309118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001429526,"about_ca_system_score_gemma":0.0001545593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004487126,"about_ca_topic_score_gemma":0.000005818022,"domain_scores_codex":[0.9980456,0.00003545394,0.001151772,0.00005986365,0.0005463262,0.0001610072],"domain_scores_gemma":[0.9979889,0.00003287067,0.001181992,0.0002309699,0.0004747235,0.00009050105],"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":[0.0001048494,0.00006475797,0.0005141854,0.0002841423,0.0001492394,0.00002205719,0.01859948,0.954924,0.00005846588,0.01417912,0.0007405943,0.01035914],"study_design_scores_gemma":[0.004905432,0.005347451,0.0008098372,0.004513694,0.00007976588,0.006305902,0.02276052,0.830909,0.005407955,0.000741245,0.117191,0.001028198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02753995,0.00009425783,0.9678209,0.0002444183,0.0009914688,0.0001426342,0.000004370045,0.0000219984,0.003139967],"genre_scores_gemma":[0.9811789,0.00006652323,0.01852887,0.0001307921,0.0000752972,0.000001872228,0.00000175255,0.000004210925,0.00001172403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.953639,"threshold_uncertainty_score":0.3283411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02651878657574229,"score_gpt":0.2466337281872999,"score_spread":0.2201149416115576,"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."}}