{"id":"W2536823992","doi":"10.1109/step.2005.7","title":"Accurate and Efficient HTML Differencing","year":2005,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; HTML element; Tree (set theory); Information retrieval; Web page; Web site; Tree structure; Document Object Model; World Wide Web; Natural language processing; Algorithm; The Internet; Binary tree; 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":[0.001802773,0.0008234057,0.001263064,0.004430105,0.0008255679,0.003081831,0.00243924,0.001387569,0.002706399],"category_scores_gemma":[0.01242433,0.0004981715,0.0006344278,0.004560222,0.0004585897,0.002916557,0.001756628,0.001129427,0.003920326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006121321,"about_ca_system_score_gemma":0.0009230574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002709183,"about_ca_topic_score_gemma":0.003418307,"domain_scores_codex":[0.9967772,0.0003385271,0.0003141709,0.0006544419,0.001717522,0.0001981235],"domain_scores_gemma":[0.992409,0.001813423,0.0006118134,0.002616521,0.002404733,0.0001443868],"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":[0.0002573706,0.000153183,0.008248987,0.0001988523,0.00005544256,0.0002522364,0.000308099,0.01598775,0.03184753,0.005019252,0.01057829,0.927093],"study_design_scores_gemma":[0.0001053206,0.0001620118,0.01332655,0.00009069364,0.00008894346,0.001954787,0.0007763874,0.7516539,0.1495282,0.02261963,0.05956459,0.0001290825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04671418,0.0007853365,0.9307929,0.0002438662,0.0001549768,0.0002023143,0.001202439,0.0164701,0.003433866],"genre_scores_gemma":[0.1814125,0.0003570608,0.809473,0.0001026442,0.00005786564,0.00008392867,0.003373445,0.0007159645,0.004423624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004430105,"threshold_uncertainty_score":0.009534061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01329653818081446,"score_gpt":0.2313119235710482,"score_spread":0.2180153853902337,"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."}}