{"id":"W1490501152","doi":"10.1007/978-3-642-03348-3_32","title":"Crawling Deep Web Using a New Set Covering Algorithm","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Crawling; Computer science; Set (abstract data type); Algorithm; Set cover problem; Greedy algorithm; Web crawler; Domain (mathematical analysis); Data mining; Artificial intelligence; World Wide Web; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008022524,0.0006188839,0.0006991513,0.001163206,0.0003743104,0.00126656,0.003955423,0.000312602,0.00002207537],"category_scores_gemma":[0.0000836669,0.0006040987,0.0002168781,0.00112168,0.0002700625,0.0009981724,0.001452129,0.0008519428,0.00003860438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003585579,"about_ca_system_score_gemma":0.001106535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374445,"about_ca_topic_score_gemma":0.0001026259,"domain_scores_codex":[0.9955546,0.00003273134,0.0005938722,0.001850764,0.001115652,0.0008524109],"domain_scores_gemma":[0.9972341,0.0002607246,0.0003458219,0.001682758,0.0001570695,0.0003195277],"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":[9.458119e-7,0.000008301317,0.00001028317,0.00000873242,0.00001507128,0.0001273387,0.0003340686,0.07332548,0.00023296,0.0006161262,0.00001480849,0.9253059],"study_design_scores_gemma":[0.000198291,0.00007201544,0.00001023136,0.000415841,0.00002353967,0.0001283298,2.257891e-7,0.9761145,0.0005532565,0.01897902,0.002807974,0.0006967591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005251149,0.0006340109,0.9967049,0.0003449906,0.0009483066,0.0001371394,0.00001288867,0.0002174574,0.0009477992],"genre_scores_gemma":[0.009473538,0.00005441757,0.987799,0.001275109,0.0009425384,8.94128e-7,0.00001523858,0.00002888964,0.0004103723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9246091,"threshold_uncertainty_score":0.9997702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02539722246381348,"score_gpt":0.2601637099273211,"score_spread":0.2347664874635076,"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."}}