{"id":"W2367671471","doi":"","title":"Detecting Near-replicas of Web Pages Based on Keywords","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval; Similarity (geometry); Search engine; Web page; World Wide Web; Web crawler; Spamdexing; Web search engine; Artificial intelligence; Web search query","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001629487,0.0001428707,0.0001984053,0.0001562795,0.000346928,0.00007662492,0.001021863,0.00005159399,0.000008351241],"category_scores_gemma":[0.000002454085,0.0001383567,0.0001245361,0.0008570525,0.00008577093,0.000122962,0.0001986416,0.0001317714,0.0001032973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002263799,"about_ca_system_score_gemma":0.0001045357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001960032,"about_ca_topic_score_gemma":0.000003489609,"domain_scores_codex":[0.9987603,0.00004063451,0.0002933912,0.0005007924,0.0001908471,0.0002140399],"domain_scores_gemma":[0.9984754,0.0001699139,0.0001416666,0.001042906,0.00009067044,0.00007941328],"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":[0.000008605369,0.0009265653,0.004693882,0.00006487346,0.0001071759,0.00001758701,0.0009223648,0.008670134,0.05321179,0.003223598,0.01504051,0.9131129],"study_design_scores_gemma":[0.0005906255,0.0001115026,0.003394122,0.00004497886,0.00002674767,0.0000478945,0.00001257123,0.7117763,0.04713358,0.0001523271,0.2362733,0.0004360361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02392079,0.0000370828,0.9738845,0.0006420558,0.00001176767,0.0001740677,0.00001305545,0.0002102882,0.001106399],"genre_scores_gemma":[0.5532626,0.00000639311,0.4461662,0.0003476599,0.00005584766,0.0000773266,0.00001208153,0.000008686348,0.00006319618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9126769,"threshold_uncertainty_score":0.5642021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01938273182328694,"score_gpt":0.2390850823125578,"score_spread":0.2197023504892708,"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."}}