{"id":"W2147979708","doi":"10.1145/967900.968022","title":"Framework for mining web content outliers","year":2004,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Outlier; Content (measure theory); Web mining; Information retrieval; World Wide Web; Web service; 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":[0.00449578,0.001590618,0.001910177,0.009274991,0.001626338,0.005238258,0.003947157,0.002230209,0.001653488],"category_scores_gemma":[0.01291416,0.0007805668,0.002778208,0.007800241,0.002066988,0.004838282,0.00352299,0.002401665,0.001176332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001900655,"about_ca_system_score_gemma":0.002925819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01012129,"about_ca_topic_score_gemma":0.008329951,"domain_scores_codex":[0.9937133,0.001554488,0.0006230058,0.00108208,0.002659222,0.0003679045],"domain_scores_gemma":[0.9935796,0.002126276,0.0008977355,0.001066548,0.002030211,0.0002995704],"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":[0.0002239658,0.0005806673,0.01945374,0.0009439131,0.00049427,0.002246032,0.001640093,0.1695397,0.006278163,0.4282931,0.01927482,0.3510316],"study_design_scores_gemma":[0.00004827313,0.00007980555,0.001878512,0.0001020969,0.0000866476,0.0005951339,0.0005656952,0.8010799,0.002335707,0.1695558,0.02360802,0.00006433149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003253691,0.0002479222,0.9934443,0.0003880232,0.00002892259,0.0002785766,0.0003657996,0.0008806591,0.001112119],"genre_scores_gemma":[0.08181082,0.0005307154,0.9130067,0.000167548,0.0001371312,0.0006782903,0.001663852,0.0001141884,0.001890701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01012129,"threshold_uncertainty_score":0.02377629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0725405980701763,"score_gpt":0.2891242805934112,"score_spread":0.2165836825232349,"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."}}