{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143673,0.001351384,0.001432256,0.00562531,0.001118901,0.00143732,0.002466266,0.001944931,0.001452734],"category_scores_gemma":[0.006536217,0.0006347207,0.0009490801,0.003650807,0.0006486489,0.002598933,0.001815703,0.00127856,0.001867382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005066115,"about_ca_system_score_gemma":0.00143882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002759557,"about_ca_topic_score_gemma":0.004936315,"domain_scores_codex":[0.9989051,0.0001133778,0.0001444185,0.0002418638,0.000495826,0.00009945106],"domain_scores_gemma":[0.9977334,0.0008475015,0.0003251603,0.0002711833,0.0007198958,0.000102879],"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":[0.0006255551,0.0004099399,0.01977829,0.0004337645,0.0002991767,0.0006656326,0.0003495339,0.03140755,0.02188433,0.003138808,0.0276675,0.8933399],"study_design_scores_gemma":[0.0001431182,0.0002065312,0.004695228,0.00006213535,0.00007576275,0.001597097,0.0002635015,0.9367577,0.02930488,0.008761059,0.01805952,0.00007353549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04700317,0.0006570068,0.9365487,0.0002918404,0.000119285,0.0005159301,0.002051204,0.01195593,0.0008570527],"genre_scores_gemma":[0.0987727,0.0002664058,0.8906405,0.0001505576,0.00005411246,0.0006199568,0.006717039,0.0004722013,0.002306533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00562531,"threshold_uncertainty_score":0.006048441,"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."}}