{"id":"W2152056009","doi":"10.1145/1526709.1526868","title":"News article extraction with template-independent wrapper","year":2009,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Template; Computer science; Information retrieval; Information extraction; Data mining; Programming language","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":[0.001560581,0.001485739,0.001565383,0.005454689,0.0006364016,0.001684243,0.001453448,0.001558401,0.001740119],"category_scores_gemma":[0.007294182,0.0007782005,0.001637095,0.003953373,0.0005463731,0.003827923,0.001515174,0.001064394,0.00429526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000380207,"about_ca_system_score_gemma":0.0007679895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008453276,"about_ca_topic_score_gemma":0.001139377,"domain_scores_codex":[0.9983847,0.0002516906,0.0002250113,0.0005741165,0.000448094,0.000116383],"domain_scores_gemma":[0.9953694,0.001532608,0.0005448717,0.001495837,0.0009423822,0.0001148855],"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":[0.000230362,0.0002517687,0.00607991,0.0004376897,0.0002504699,0.0008482886,0.0002140486,0.01887364,0.0308705,0.001962382,0.01671756,0.9232633],"study_design_scores_gemma":[0.00005376901,0.0002402775,0.004622853,0.00005669096,0.0002575243,0.001725045,0.0001745752,0.7809541,0.1776354,0.01211454,0.02205979,0.0001053722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03121665,0.0008028183,0.9458761,0.0002641618,0.0001817139,0.0002152086,0.001277493,0.01864514,0.001520593],"genre_scores_gemma":[0.1553703,0.0006453681,0.8289565,0.0002805915,0.0002716183,0.0002518734,0.007688016,0.001009355,0.005526286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005454689,"threshold_uncertainty_score":0.008253276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01283927497978943,"score_gpt":0.2512661544123126,"score_spread":0.2384268794325232,"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."}}