{"id":"W2094060849","doi":"10.1016/j.datak.2010.03.007","title":"Ranking bias in deep web size estimation using capture recapture method","year":2010,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; State Key Laboratory of Novel Software Technology","keywords":"Ranking (information retrieval); Computer science; Estimation; Sampling (signal processing); Data mining; Process (computing); Matching (statistics); Mark and recapture; Rank (graph theory); Limit (mathematics); Statistics; Information retrieval; Mathematics","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":[0.01633218,0.0006481474,0.001334238,0.002630101,0.0007127601,0.001376731,0.003413481,0.001718978,0.001395158],"category_scores_gemma":[0.04658943,0.0008022934,0.001106185,0.001950856,0.001113598,0.002739721,0.001404478,0.001309363,0.0004684526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009392276,"about_ca_system_score_gemma":0.0006469178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004529726,"about_ca_topic_score_gemma":0.005108615,"domain_scores_codex":[0.9954774,0.002397901,0.0001695105,0.0009810714,0.0006238922,0.0003504006],"domain_scores_gemma":[0.9398468,0.04928198,0.002936032,0.005453202,0.002061409,0.0004206027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004939754,0.0002090281,0.1513406,0.0003782659,0.001305043,0.0005498679,0.0003865747,0.4513527,0.007002406,0.06371681,0.006325785,0.3169389],"study_design_scores_gemma":[0.00001674243,0.00005036124,0.0109271,0.00001854077,0.00009993631,0.0001244517,0.00003584382,0.9651141,0.002610695,0.02025442,0.0007128011,0.00003503654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1211228,0.0004393273,0.8766174,0.0001859157,0.00005889485,0.00003705051,0.0001817816,0.0005524368,0.000804336],"genre_scores_gemma":[0.8827783,0.000195953,0.1128196,0.0002302114,0.0001107628,0.0001023266,0.0006749718,0.0001551392,0.002932728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01633218,"threshold_uncertainty_score":0.08637387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04137654040511619,"score_gpt":0.3090537414834847,"score_spread":0.2676772010783685,"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."}}