{"id":"W2752935397","doi":"10.1504/ijwet.2017.086415","title":"Estimating similarity of rich internet pages using visual information","year":2017,"lang":"en","type":"article","venue":"International Journal of Web Engineering and Technology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Similarity (geometry); The Internet; Information retrieval; World Wide Web; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008618836,0.0005646723,0.0008851304,0.007919881,0.0002741037,0.001411546,0.0005975458,0.0009481162,0.0007807055],"category_scores_gemma":[0.005731983,0.0002688484,0.0006992908,0.003118179,0.0003878488,0.002270598,0.0009539138,0.0004410958,0.0006163773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004240743,"about_ca_system_score_gemma":0.0003538101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0022904,"about_ca_topic_score_gemma":0.002506648,"domain_scores_codex":[0.9991229,0.0001566676,0.00007226644,0.0002303062,0.0003407543,0.00007701465],"domain_scores_gemma":[0.997422,0.001137637,0.0003870117,0.0002855415,0.0006327872,0.0001350761],"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":[0.001275049,0.0008970147,0.07800949,0.000748531,0.0004480946,0.0008409782,0.0007875379,0.1575322,0.0923664,0.006159665,0.003737725,0.6571974],"study_design_scores_gemma":[0.00002121929,0.000237202,0.02777226,0.00002207678,0.00007886946,0.0004646449,0.0001686074,0.9519955,0.01402997,0.004211041,0.0009584409,0.00004018838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6214259,0.0009364265,0.373172,0.00006092854,0.00006070165,0.0001991992,0.0005956611,0.001451231,0.002098018],"genre_scores_gemma":[0.9083441,0.000228009,0.08946726,0.00002059044,0.00003378645,0.00005898791,0.001000669,0.00008264416,0.0007639469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007919881,"threshold_uncertainty_score":0.004558146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01111159971823721,"score_gpt":0.2672239810553102,"score_spread":0.256112381337073,"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."}}