{"id":"W7095329675","doi":"","title":"Combining Multiple Sources of Evidence in Web Information Extraction. Toronto 2008. In: Foundations of Intelligent Systems","year":2008,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Information extraction; Ontology; Ranking (information retrieval); Selection (genetic algorithm); Domain (mathematical analysis); Web page; HTML element; Data extraction","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010589,0.001456882,0.002336191,0.01528258,0.00212174,0.00849558,0.002099608,0.002458946,0.004669559],"category_scores_gemma":[0.04412125,0.002266636,0.001615666,0.01559518,0.002213155,0.009590751,0.004817002,0.002122586,0.001327066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004209515,"about_ca_system_score_gemma":0.00829552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06702279,"about_ca_topic_score_gemma":0.2147005,"domain_scores_codex":[0.993535,0.002069132,0.0008631104,0.0005343652,0.002743621,0.0002547845],"domain_scores_gemma":[0.9596662,0.02839696,0.001520212,0.002296452,0.007510133,0.0006101181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005471694,0.0001456397,0.02497309,0.005231332,0.001632015,0.002159847,0.001910957,0.01664659,0.003614829,0.03032441,0.05520095,0.8576133],"study_design_scores_gemma":[0.0003098445,0.0002584136,0.05637879,0.01146718,0.007532877,0.004308899,0.006439258,0.3050231,0.03608163,0.3211839,0.2504238,0.0005922403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04133127,0.210029,0.6798703,0.02092368,0.001278314,0.0008599181,0.01591321,0.003028072,0.02676626],"genre_scores_gemma":[0.2948969,0.03987803,0.6468495,0.0006610819,0.0007531663,0.0002551529,0.007811383,0.0003373302,0.008557557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06702279,"threshold_uncertainty_score":0.1332654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1072378682874622,"score_gpt":0.3088743515709479,"score_spread":0.2016364832834857,"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."}}