{"id":"W3100308720","doi":"10.3233/faia200731","title":"Focused Crawler Strategy Based on Improved Energy Landscape Paving Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Social Science Fund of China","keywords":"Web crawler; Focused crawler; Hyperlink; Domain (mathematical analysis); Computer science; Crawling; Data mining; Information retrieval; Web page; World Wide Web; Mathematics; Web navigation; Static web page","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"],"consensus_categories":[],"category_scores_codex":[0.0001460775,0.0003060056,0.0003871617,0.000348133,0.0001744655,0.00026949,0.0007673577,0.000220493,0.00003433528],"category_scores_gemma":[0.00001203171,0.000309942,0.0001165877,0.0002753653,0.000104013,0.0001386625,0.0001246687,0.0003379207,0.0000433187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003795484,"about_ca_system_score_gemma":0.0001170238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000347158,"about_ca_topic_score_gemma":0.00003602216,"domain_scores_codex":[0.9981627,0.0000229944,0.0004858224,0.0008624924,0.000217656,0.0002483579],"domain_scores_gemma":[0.9988319,0.00008008827,0.0001891014,0.0006865381,0.0000620005,0.0001503497],"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":[0.000004058187,0.00003114158,0.000004627701,0.00000718053,0.00002158394,0.000005151746,0.00003211216,0.0003999816,0.00001296475,0.1891678,0.00124583,0.8090675],"study_design_scores_gemma":[0.00002953981,0.00007748888,0.000002134404,0.00005194761,0.00003174497,5.988899e-7,0.00005531067,0.8176665,0.0003302358,0.1178116,0.06358285,0.0003600536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[3.869491e-7,0.0003362487,0.9682203,0.0006439247,0.00012915,0.0001746166,0.00007456388,0.00009505176,0.03032578],"genre_scores_gemma":[0.08196874,0.002568576,0.8411475,0.005266222,0.003198369,0.001368075,0.001778821,0.000332608,0.06237104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8172665,"threshold_uncertainty_score":0.9999353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03050407268648987,"score_gpt":0.2442026541807938,"score_spread":0.2136985814943039,"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."}}