{"id":"W2004782477","doi":"10.1109/hicss.2010.58","title":"An n-Gram Based Approach to Multi-Labeled Web Page Genre Classification","year":2010,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Killam Trusts","keywords":"Computer science; Web page; n-gram; Classifier (UML); Popularity; Artificial intelligence; Support vector machine; Information retrieval; Set (abstract data type); Precision and recall; World Wide Web; Language model","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007136168,0.0001205207,0.0001037513,0.0001064343,0.00016902,0.0002037756,0.0008205891,0.0001281971,0.00005027138],"category_scores_gemma":[0.00007197637,0.0001035609,0.00003946704,0.0004871726,0.0000220557,0.0003229328,0.00006113973,0.0002599741,0.0002448467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001859936,"about_ca_system_score_gemma":0.00009801559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001128485,"about_ca_topic_score_gemma":0.00002747299,"domain_scores_codex":[0.9987761,0.0001067737,0.0001865294,0.0004593379,0.0002082428,0.0002629491],"domain_scores_gemma":[0.9987261,0.00003874253,0.00005092744,0.0007958869,0.0001192123,0.0002690773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008222508,0.0004989504,0.002673334,0.00001166991,0.000005027348,0.000001322644,0.0004831235,0.0001024218,0.7257031,0.2425429,0.0005254136,0.02744449],"study_design_scores_gemma":[0.0002998878,0.00003515076,0.005581406,0.000001404671,0.000002043818,0.000001792935,0.00004772108,0.9762856,0.01507398,0.00007872636,0.002420802,0.0001714421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07143016,0.000002618821,0.923407,0.001031139,0.0003063334,0.0002690399,0.00000334751,0.0004972885,0.003053092],"genre_scores_gemma":[0.592518,1.542474e-7,0.4063276,0.0007207776,0.00003447843,0.00002551582,0.00001804518,0.00000524975,0.0003501859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9761832,"threshold_uncertainty_score":0.422309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07747908222797885,"score_gpt":0.3240996072120708,"score_spread":0.246620524984092,"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."}}