{"id":"W2164704937","doi":"10.1109/wi-iat.2009.79","title":"Classifying Web Pages by Genre: An n-Gram Approach","year":2009,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"n-gram; Computer science; Web page; Set (abstract data type); Information retrieval; Range (aeronautics); Byte; Support vector machine; Artificial intelligence; Data mining; World Wide Web; Language model; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777455,0.001053152,0.001144955,0.009769361,0.001042956,0.001843577,0.0007722909,0.001030108,0.00206916],"category_scores_gemma":[0.008766185,0.0002399524,0.001100234,0.005392997,0.0006046996,0.002336226,0.001011535,0.0009822194,0.002282521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000603869,"about_ca_system_score_gemma":0.0007051949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003426789,"about_ca_topic_score_gemma":0.004992045,"domain_scores_codex":[0.9982048,0.0005900609,0.0002493974,0.0003032144,0.0005022662,0.0001501833],"domain_scores_gemma":[0.9954219,0.002257964,0.0004798294,0.0005117899,0.001083589,0.0002448258],"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":[0.001227572,0.0007739305,0.03905606,0.0004251354,0.0002351917,0.0004293877,0.0008220294,0.006928304,0.02400198,0.002622156,0.007356214,0.916122],"study_design_scores_gemma":[0.0001366814,0.0009269477,0.07699642,0.0002617418,0.0004544529,0.002028565,0.002331759,0.8523761,0.01621067,0.03088102,0.0171596,0.000236039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4083104,0.003852731,0.5634565,0.001590562,0.0005956955,0.00118275,0.005118253,0.004187829,0.01170536],"genre_scores_gemma":[0.6220639,0.001082431,0.3669948,0.0002614751,0.0004352202,0.0004433578,0.004078497,0.0002000019,0.004440304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009769361,"threshold_uncertainty_score":0.009400189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04927804363426996,"score_gpt":0.2888195418324475,"score_spread":0.2395414981981775,"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."}}