{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104616,0.00005196346,0.0000665699,0.0000489562,0.0000661025,0.0001438673,0.0002465816,0.00001353746,0.00002310584],"category_scores_gemma":[0.00001474743,0.00003777772,0.00001721203,0.0001398289,0.0000113183,0.0001351751,0.0001772842,0.0000356203,0.00006924573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007592006,"about_ca_system_score_gemma":0.000008916538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001936674,"about_ca_topic_score_gemma":0.00001171788,"domain_scores_codex":[0.9995118,0.00001275086,0.00007978464,0.0001893662,0.0000877198,0.0001185547],"domain_scores_gemma":[0.9996354,0.00003370733,0.00001942106,0.0002450375,0.00001283094,0.00005362548],"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":[0.000001986509,0.000121544,0.002378464,0.0000109961,0.00005067752,0.00001159456,0.002291477,0.005014618,0.003690373,0.08362033,0.004726398,0.8980815],"study_design_scores_gemma":[0.00009068653,0.00000936617,0.004060357,0.000004982697,0.000004256716,0.000004748628,0.00002962142,0.9921027,0.001141434,0.00004976497,0.002418497,0.00008356834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3849506,0.00005606982,0.6093055,0.001411938,0.00002849777,0.00001441391,6.648006e-7,0.0001007682,0.004131521],"genre_scores_gemma":[0.9679607,0.000005546512,0.03097722,0.0002545376,0.00003247389,8.506443e-7,7.102004e-7,0.000001494283,0.000766521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9870881,"threshold_uncertainty_score":0.1540531,"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."}}