{"id":"W2153487386","doi":"10.1109/iscc.2005.155","title":"WCOND-Mine: Algorithm for Detecting Web Content Outliers from Web Documents","year":2005,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Outlier; Computer science; Web mining; Domain (mathematical analysis); Data mining; Web content; Web analytics; Competitor analysis; Information retrieval; Web service; Web page; World Wide Web; Web intelligence; Web modeling; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.000138156,0.0001286702,0.0001304786,0.00007281564,0.0002113052,0.0001516959,0.0005144769,0.00006567213,0.00008178259],"category_scores_gemma":[0.00001286819,0.0001166827,0.0001028156,0.0001801188,0.00002281285,0.0003669554,0.0001326544,0.00008757386,0.00008888894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007467445,"about_ca_system_score_gemma":0.00003975173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009355127,"about_ca_topic_score_gemma":0.00007990954,"domain_scores_codex":[0.9989506,0.00001287908,0.0002611559,0.0003899725,0.0001402395,0.0002451808],"domain_scores_gemma":[0.999223,0.00007740075,0.00009660918,0.0004170324,0.00008617337,0.00009979329],"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":[0.000001603682,0.0000464224,0.00009669312,0.000001366104,0.00002221008,4.006612e-7,0.00006056011,0.000008607103,0.009106793,0.004275705,0.003527105,0.9828525],"study_design_scores_gemma":[0.0006895145,0.0000986741,0.0001284646,0.00000790821,0.00001160954,0.000005298328,0.0001074404,0.6897988,0.0876153,0.001668182,0.2195899,0.0002788488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01370786,0.00004383925,0.9808326,0.001267536,0.0001283063,0.0004266295,0.00001844707,0.0006860003,0.002888821],"genre_scores_gemma":[0.349985,0.00001393669,0.6453323,0.0007927225,0.0001576407,0.0002488496,0.000003842482,0.00001054749,0.003455137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9825737,"threshold_uncertainty_score":0.4758184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02507518883317332,"score_gpt":0.2719936284313389,"score_spread":0.2469184395981656,"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."}}