{"id":"W2121315872","doi":"10.1007/s10791-013-9230-7","title":"Discover hidden web properties by random walk on bipartite graph","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":11,"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; Nanjing University","keywords":"Zipf's law; Crawling; Simple random sample; Random walk; Sampling (signal processing); Bipartite graph; Statistics; Computer science; Sample size determination; Sample (material); Bernoulli's principle; Population; Mathematics; Graph; Theoretical computer science","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":[0.0006936954,0.0006015337,0.001191527,0.00500939,0.0006803951,0.001262102,0.0009171172,0.001476467,0.001332494],"category_scores_gemma":[0.006454105,0.0007158424,0.001027045,0.002416113,0.000810214,0.003526289,0.000926211,0.001109065,0.0005484079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006540375,"about_ca_system_score_gemma":0.0005645808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003279721,"about_ca_topic_score_gemma":0.005123858,"domain_scores_codex":[0.9993382,0.0002151849,0.00003314131,0.0001819096,0.0001361052,0.00009545631],"domain_scores_gemma":[0.993468,0.004428194,0.0007872588,0.000676261,0.0003815564,0.000258807],"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":[0.002032819,0.001571557,0.113534,0.001432239,0.001104718,0.00183215,0.0009285028,0.4128532,0.05285919,0.1325716,0.01901474,0.2602652],"study_design_scores_gemma":[0.00002657625,0.00004502894,0.002637314,0.00001446041,0.00004700684,0.0001109718,0.00004997443,0.9417186,0.001270377,0.05362458,0.0004420239,0.00001308435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5718945,0.0008809852,0.41945,0.0008579242,0.00004232299,0.0001183634,0.001983277,0.002010462,0.002762224],"genre_scores_gemma":[0.9553607,0.0003024278,0.04074347,0.0001050237,0.00006371925,0.00004821331,0.001919499,0.0001121971,0.001344797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00500939,"threshold_uncertainty_score":0.006521225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008604713258223986,"score_gpt":0.189222311925318,"score_spread":0.180617598667094,"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."}}