{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001340961,0.001184319,0.002894194,0.006474771,0.001622836,0.002251062,0.002589686,0.002244744,0.003637366],"category_scores_gemma":[0.006709521,0.001045255,0.00225813,0.005241362,0.000739948,0.003560972,0.002941073,0.001420929,0.001364784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008944329,"about_ca_system_score_gemma":0.001636692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004325528,"about_ca_topic_score_gemma":0.008517152,"domain_scores_codex":[0.9972454,0.0004747294,0.000254307,0.0005508966,0.001271185,0.0002034454],"domain_scores_gemma":[0.9951533,0.002073879,0.0002438501,0.001547872,0.0007742189,0.0002067943],"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":[0.0002545464,0.0004798568,0.004702393,0.0002828869,0.0004037599,0.0003029057,0.0002269872,0.07680118,0.01689374,0.01343115,0.01548583,0.8707348],"study_design_scores_gemma":[0.00003246089,0.00009199203,0.0008000909,0.00001741976,0.00009552101,0.0003106585,0.00003095975,0.9746514,0.004731399,0.01455191,0.004661889,0.00002426191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02815794,0.0005461796,0.9641528,0.0001844029,0.000193467,0.0001669353,0.000444402,0.004352668,0.001801282],"genre_scores_gemma":[0.1076135,0.000235989,0.8853235,0.0001337209,0.0001714446,0.0002615066,0.001712325,0.0005185639,0.004029545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006474771,"threshold_uncertainty_score":0.01216823,"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."}}