{"id":"W2059414344","doi":"10.1007/s10044-014-0432-4","title":"An investigation of implicit features in compression-based learning for comparing webpages","year":2014,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Feature (linguistics); Feature selection; Web page; Compression (physics); Task (project management); Phishing; Pattern recognition (psychology); Artificial intelligence; Cover (algebra); Feature vector; Image compression; Space (punctuation); Data compression; Selection (genetic algorithm); Information retrieval; Data mining; Image (mathematics); The Internet; Image processing; World Wide Web","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":[0.0003762139,0.00009354721,0.0002668737,0.0002623156,0.0001231177,0.00007915077,0.0003567746,0.00003721508,0.000002632345],"category_scores_gemma":[0.00001178466,0.00008711882,0.0000734987,0.0006510003,0.00004658522,0.00009377181,0.0000704128,0.00008486659,7.469974e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001367948,"about_ca_system_score_gemma":0.0000116116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003206887,"about_ca_topic_score_gemma":0.0003828162,"domain_scores_codex":[0.9990261,0.0001018673,0.0002596145,0.0003738207,0.0001122797,0.0001263591],"domain_scores_gemma":[0.999041,0.0002483704,0.0001506452,0.0004138578,0.00007741524,0.0000687787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001117913,0.0000607531,0.8100359,0.00003139062,0.00002884257,4.914507e-8,0.0001962406,0.0635607,0.002746855,0.001967629,0.000004339749,0.1213662],"study_design_scores_gemma":[0.0001146601,0.00001936798,0.4071428,0.000004921411,0.00002983466,1.809793e-7,0.0000112721,0.5900559,0.001104711,0.001410445,0.0000462075,0.00005963114],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2436714,0.00001975668,0.7558832,0.0001878823,0.000005349561,0.0001755289,0.000001544163,0.0000360027,0.00001938741],"genre_scores_gemma":[0.9742092,0.000001935479,0.0254674,0.00009190795,0.0000281555,0.0001477949,0.00004633752,0.000004180041,0.000003079586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7305378,"threshold_uncertainty_score":0.3552603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01604752687691857,"score_gpt":0.2793494901573245,"score_spread":0.2633019632804059,"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."}}