{"id":"W4232386687","doi":"10.1007/978-0-387-39940-9_3972","title":"Visual Web Information Extraction","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Information extraction; Computer science; Extraction (chemistry); World Wide Web; Information retrieval; Chemistry; Chromatography","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":[0.000535753,0.0003316464,0.0005300196,0.0005722861,0.00007968849,0.0001566907,0.0008360641,0.0002294714,0.00004869682],"category_scores_gemma":[0.00006626183,0.000318664,0.000158333,0.000133119,0.00003385349,0.002745071,0.0002210106,0.0003250731,0.000587318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000628745,"about_ca_system_score_gemma":0.0002474913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001198838,"about_ca_topic_score_gemma":0.00001146925,"domain_scores_codex":[0.997673,0.00004325047,0.0009155,0.0004011693,0.0007423366,0.0002247109],"domain_scores_gemma":[0.9974438,0.00009535335,0.0009403578,0.001205766,0.0001889086,0.0001258335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002560686,0.0001382446,0.00004877062,0.001039698,0.000416804,0.0001057718,0.0005780787,0.0002161085,0.0002119645,0.3198414,0.2440641,0.4333135],"study_design_scores_gemma":[0.0001734528,0.00007472807,0.00001416836,0.0004711242,0.00007695238,0.00003097537,0.00002454601,0.01194089,0.00001233337,0.00009940722,0.9867205,0.0003608933],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00003261606,0.0008254405,0.07844229,0.00006660717,0.001797706,0.0003037387,0.001077136,0.0002214796,0.917233],"genre_scores_gemma":[0.01184568,0.01111291,0.02434407,0.0002566841,0.003762431,0.00006139569,0.01830146,0.0001118523,0.9302035],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7426564,"threshold_uncertainty_score":0.9999266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01116611132904541,"score_gpt":0.24656012360515,"score_spread":0.2353940122761046,"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."}}