{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005952448,0.0001529565,0.0002141862,0.0002484134,0.0001698485,0.0002449452,0.003080039,0.00003010939,0.0001575488],"category_scores_gemma":[0.0002427961,0.0001029445,0.00006597288,0.000702623,0.00006810174,0.0009391605,0.001209084,0.00009257252,0.0006961977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000214397,"about_ca_system_score_gemma":0.00008746487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000277888,"about_ca_topic_score_gemma":0.0007837945,"domain_scores_codex":[0.9983179,0.00008109201,0.000264363,0.0006740842,0.0003012345,0.0003613367],"domain_scores_gemma":[0.9969209,0.0004557066,0.0001073936,0.0023494,0.00003872043,0.000127859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003597839,0.0002505816,0.1184923,0.00005119202,0.0006854907,0.0002176713,0.0009381491,0.0001030287,0.05685702,0.01437997,0.2061457,0.6018429],"study_design_scores_gemma":[0.001065985,0.00002438004,0.002395343,0.0001982029,0.00007733131,0.00001080258,0.00004279646,0.1348247,0.002455202,0.0011588,0.8571342,0.0006122898],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1007089,0.001589725,0.8451302,0.03590384,0.001215721,0.0001831593,0.0001652464,0.001360727,0.01374246],"genre_scores_gemma":[0.9706023,0.00004721089,0.02269148,0.0007288522,0.0002204379,0.000004009802,0.00002352325,0.00001357397,0.005668646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8698933,"threshold_uncertainty_score":0.8948445,"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."}}