{"id":"W4366967382","doi":"10.1109/wi-iat55865.2022.00097","title":"Web Mining from Interpretable Compressed Representation of Sparse Web","year":2022,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Web page; Web mining; Data Web; Web modeling; Information retrieval; Web intelligence; Web mapping; Bitmap; World Wide Web; Data mining; Web navigation; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001776951,0.00006923695,0.0001770403,0.0001228847,0.0001068742,0.00006667423,0.000862524,0.00001308788,0.0007883211],"category_scores_gemma":[0.00003462517,0.00006844493,0.00006845389,0.000567874,0.00001948965,0.0003162034,0.0008170668,0.00007657005,0.00001537202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001694904,"about_ca_system_score_gemma":0.00005679599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006076154,"about_ca_topic_score_gemma":0.00003355071,"domain_scores_codex":[0.9989134,0.0001225789,0.000232771,0.0003182068,0.0002883379,0.0001246777],"domain_scores_gemma":[0.9989915,0.0001679932,0.0001226917,0.0006479569,0.00003135402,0.0000385278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001148607,0.0010093,0.1101293,0.00003901763,0.0009029119,0.000123009,0.01784601,0.04371398,0.4619961,0.01817628,0.2479504,0.09799889],"study_design_scores_gemma":[0.0002857659,0.00003822927,0.0006616664,0.000008551692,0.00001977568,0.000001988843,0.001075757,0.9866567,0.005951986,0.0002094675,0.004987991,0.0001021043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8207314,0.00009422805,0.1621567,0.000613711,0.0003467365,0.00006620501,0.000104814,0.000181389,0.01570478],"genre_scores_gemma":[0.9581402,0.00000383244,0.04062685,0.0001418269,0.00001829096,0.000009681376,0.00005466407,0.00000419247,0.001000476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9429427,"threshold_uncertainty_score":0.8631563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02898493174544723,"score_gpt":0.2614506699920739,"score_spread":0.2324657382466267,"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."}}