{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001380027,0.0002238119,0.0002797583,0.0003047939,0.00007822678,0.0002647597,0.00189518,0.0001497911,0.00001879767],"category_scores_gemma":[0.001391393,0.0002227019,0.00004740358,0.001139669,0.00001255582,0.001311331,0.000832617,0.0006233147,0.00002930244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004112503,"about_ca_system_score_gemma":0.00008586884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006597544,"about_ca_topic_score_gemma":0.0003269681,"domain_scores_codex":[0.9984485,0.00006753288,0.0003179018,0.0006311587,0.0001828447,0.0003520474],"domain_scores_gemma":[0.9976859,0.000487885,0.00008022657,0.001594738,0.00005195821,0.0000993042],"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":[0.000005865876,0.0001599249,0.001187569,0.0002368207,0.0001340133,0.0001031899,0.004796076,0.05869979,0.1285345,0.005520449,0.001189216,0.7994326],"study_design_scores_gemma":[0.0002063887,0.000003138769,0.0002775546,0.0000806287,0.00002428847,0.00003142155,0.00002194368,0.9936414,0.000518282,0.00004425647,0.004893872,0.000256789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01559837,0.0004736361,0.9825179,0.00008067989,0.0007853129,0.00007229389,0.00004719188,0.0002283072,0.0001963344],"genre_scores_gemma":[0.2272448,0.000005427165,0.7723539,0.00001836734,0.0001790374,0.000003968597,0.0001453089,0.0000212157,0.00002802503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9349416,"threshold_uncertainty_score":0.9081521,"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."}}