{"id":"W4246166785","doi":"10.1109/wi.2004.10005","title":"Clustering Web Surfers with Probabilistic Models in a Real Application","year":2005,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada); York University","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Probabilistic logic; Machine learning; Artificial intelligence","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"],"consensus_categories":[],"category_scores_codex":[0.000624685,0.0004306363,0.0003306818,0.0005322036,0.0001166728,0.0006192523,0.003971954,0.0001206218,0.000135769],"category_scores_gemma":[0.0001048455,0.000399319,0.00008328473,0.0005852666,0.0001714232,0.002044704,0.0005822749,0.000432143,0.0004836872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004130178,"about_ca_system_score_gemma":0.0003040638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002566463,"about_ca_topic_score_gemma":0.001727937,"domain_scores_codex":[0.9964344,0.00009033374,0.0007010885,0.001182171,0.001013625,0.0005784031],"domain_scores_gemma":[0.9976575,0.0001602289,0.00028546,0.001257978,0.0004688471,0.00016999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002059732,0.0006317804,0.0007479538,0.00006689725,0.0001036106,0.00005451405,0.001162901,0.1427639,0.001023886,0.6041993,0.0009494192,0.2480899],"study_design_scores_gemma":[0.0003302607,0.0001733925,0.000194902,0.0002194617,0.00000913701,0.00001045367,0.0001517218,0.9808796,0.0007793393,0.01405198,0.002705937,0.000493824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02251289,0.00002010289,0.9238992,0.004260015,0.001024878,0.000962486,0.00007821054,0.0003795172,0.0468627],"genre_scores_gemma":[0.9694934,0.0003188049,0.02808039,0.0004477974,0.0002904042,0.0002281607,0.00008123177,0.00002974005,0.001030075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9469805,"threshold_uncertainty_score":0.9998459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07176416831107739,"score_gpt":0.3081671451329525,"score_spread":0.2364029768218751,"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."}}