{"id":"W2025635041","doi":"10.1145/1754393.1754394","title":"Detecting visually similar Web pages","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Gestalt psychology; Web page; Similarity (geometry); World Wide Web; Realization (probability); Information retrieval; Phishing; Artificial intelligence; The Internet; Image (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":[0.0001828201,0.0001723844,0.0001493528,0.0006285537,0.0001587063,0.0001119365,0.001674999,0.0003648911,0.0001151852],"category_scores_gemma":[0.0001455516,0.0001720235,0.00008693312,0.0007139886,0.0001036822,0.0002888106,0.000045822,0.001093369,0.0002175511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003207076,"about_ca_system_score_gemma":0.00003336269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002801259,"about_ca_topic_score_gemma":0.0005310873,"domain_scores_codex":[0.9988413,0.00002692244,0.0002167882,0.0004666184,0.0001502215,0.0002980873],"domain_scores_gemma":[0.9985304,0.0001399169,0.00007207292,0.001131769,0.00006879863,0.00005702451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001685509,0.0001521282,0.0002277789,0.000008906815,0.0000590629,0.00002476191,0.0002903735,0.00006297451,0.155866,0.00853595,0.0003423157,0.8344129],"study_design_scores_gemma":[0.0006113944,0.0009021828,0.0003165044,0.0000405821,0.00002489617,0.0004092245,0.00009981285,0.02805362,0.899895,0.02836155,0.04077437,0.00051083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2533928,0.00001491772,0.7378473,0.004542626,0.001864341,0.0001049053,0.000001543656,0.001689888,0.0005416301],"genre_scores_gemma":[0.9649818,0.0000161858,0.0343467,0.0002426297,0.00004719804,0.00003483353,3.771435e-7,0.00001744531,0.0003128645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8339021,"threshold_uncertainty_score":0.7014916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0128471117380512,"score_gpt":0.2488890762803148,"score_spread":0.2360419645422636,"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."}}