{"id":"W1482288948","doi":"10.3233/wia-2012-0232","title":"Selecting queries from sample to crawl deep web data sources","year":2012,"lang":"en","type":"article","venue":"Web Intelligence and Agent Systems An International Journal","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Nanjing University","keywords":"Deep Web; Sample (material); Computer science; Information retrieval; World Wide Web; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001095286,0.0001781339,0.0002137338,0.0002579772,0.0003170522,0.001794021,0.002620588,0.00005238204,0.00009980548],"category_scores_gemma":[0.0002937012,0.0001488533,0.00005358007,0.0002221051,0.00003360676,0.002845314,0.000743936,0.0002226337,0.00008356309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006033135,"about_ca_system_score_gemma":0.00008842918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001037412,"about_ca_topic_score_gemma":0.0001913356,"domain_scores_codex":[0.9979315,0.0001453037,0.0005118003,0.0004216213,0.0006305109,0.0003592931],"domain_scores_gemma":[0.9983513,0.000212427,0.0002486204,0.0005733829,0.0002186049,0.0003956435],"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":[0.00006577556,0.0006220163,0.5936841,0.00003616547,0.001664833,0.0001541975,0.02309654,0.006036381,0.007379674,0.0327741,0.007484734,0.3270015],"study_design_scores_gemma":[0.0002465884,0.0001950916,0.009255474,0.0004659538,0.00009052712,0.0009005224,0.00956246,0.7032399,0.001663477,0.0008376223,0.2725759,0.0009665104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2856731,0.0009715656,0.710245,0.000430879,0.002268381,0.00005719473,0.0001449059,0.00006091751,0.0001480431],"genre_scores_gemma":[0.9784749,0.0003051784,0.01861754,0.0002926529,0.002119337,0.000004634018,0.00008012201,0.00001093791,0.00009467076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6972035,"threshold_uncertainty_score":0.9992422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07823562605587984,"score_gpt":0.3229699100774922,"score_spread":0.2447342840216123,"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."}}