{"id":"W2508222813","doi":"10.1007/s11280-016-0410-4","title":"Crawling ranked deep Web data sources","year":2016,"lang":"en","type":"article","venue":"World Wide Web","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Crawling; Ranking (information retrieval); Web crawler; Information retrieval; Deep Web; Hyperlink; Web search query; Variety (cybernetics); Web page; Data mining; Learning to rank; World Wide Web; Search engine; Artificial intelligence; The Internet","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002314832,0.001354676,0.001280556,0.0235228,0.001715134,0.003640346,0.001427407,0.001484219,0.001565328],"category_scores_gemma":[0.02046319,0.001005208,0.001392519,0.01519511,0.0005241667,0.00409341,0.002507459,0.001609911,0.001654203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044013,"about_ca_system_score_gemma":0.003540331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01126132,"about_ca_topic_score_gemma":0.0384986,"domain_scores_codex":[0.9958781,0.0005031315,0.0004415392,0.0004700963,0.002374949,0.0003321376],"domain_scores_gemma":[0.9867908,0.004809621,0.0009664129,0.002571285,0.004293388,0.0005684369],"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":[0.0005524491,0.001373676,0.1297906,0.002558257,0.001321781,0.002047802,0.001396028,0.0130618,0.02823819,0.01214191,0.1099397,0.6975778],"study_design_scores_gemma":[0.0001419389,0.0005091097,0.07508997,0.0008256207,0.001468619,0.003753917,0.002183624,0.653421,0.07217038,0.06536436,0.1248577,0.0002137342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5387827,0.008243063,0.3185281,0.00271101,0.0008562956,0.00144737,0.08949837,0.02653361,0.01339954],"genre_scores_gemma":[0.5287319,0.002655912,0.3061214,0.0004955386,0.0002892415,0.0004858818,0.1495494,0.001549268,0.01012138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0235228,"threshold_uncertainty_score":0.02239156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02944221598943287,"score_gpt":0.2526845032144845,"score_spread":0.2232422872250516,"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."}}