{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002167648,0.000111514,0.0001025707,0.0001483567,0.0001447471,0.0007285004,0.0003425946,0.00006922973,0.00007060746],"category_scores_gemma":[0.0001031842,0.00008251806,0.00005745373,0.000405515,0.00003132957,0.005295907,0.0000597008,0.0001298966,0.001736952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003806556,"about_ca_system_score_gemma":0.00004039179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000705081,"about_ca_topic_score_gemma":0.000001174872,"domain_scores_codex":[0.9989814,0.00003815541,0.0002793106,0.0001108242,0.0004044168,0.0001859131],"domain_scores_gemma":[0.9993744,0.00003880611,0.0001189313,0.0002867522,0.0001094982,0.00007164221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001306336,0.0002586937,0.00205544,0.000215465,0.000177405,0.000002748483,0.01590895,0.001100304,0.03970342,0.02197419,0.5408679,0.3764291],"study_design_scores_gemma":[0.009899545,0.001587879,0.00938682,0.0002156077,0.00003084236,0.00004112798,0.0002840151,0.3420992,0.2272429,0.008431642,0.3991634,0.001617096],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9132439,0.0001035254,0.06682483,0.003290104,0.001845628,0.0008506338,0.000013309,0.0006033828,0.01322461],"genre_scores_gemma":[0.998154,0.00001487045,0.0002743995,0.001025725,0.00005567139,0.00001972156,0.00001204281,0.000004039427,0.000439483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.374812,"threshold_uncertainty_score":0.9990403,"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."}}