{"id":"W1972924401","doi":"10.14778/1920841.1920947","title":"Building ranked mashups of unstructured sources with uncertain information","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mashup; Computer science; Ranking (information retrieval); Information retrieval; Rank (graph theory); Probabilistic logic; Information extraction; Semantics (computer science); Database; World Wide Web; Data mining; Web service; Artificial intelligence; Web modeling","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":[0.002731234,0.001094989,0.00106761,0.001557466,0.001206341,0.002526201,0.001741999,0.0009075924,0.001505779],"category_scores_gemma":[0.01040723,0.0008647961,0.001200409,0.002355053,0.001140425,0.005428982,0.003852963,0.001475358,0.0007402739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006436169,"about_ca_system_score_gemma":0.001015325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002048713,"about_ca_topic_score_gemma":0.003776427,"domain_scores_codex":[0.9967864,0.0009445148,0.0002236523,0.0006373064,0.001192651,0.0002154907],"domain_scores_gemma":[0.9945796,0.002823736,0.0004889204,0.001318713,0.0005619757,0.000227089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001162924,0.0005160036,0.005620344,0.0009827641,0.0006406984,0.002572374,0.00328123,0.4397057,0.07857477,0.1396697,0.01348204,0.3137915],"study_design_scores_gemma":[0.00006279536,0.0001402531,0.0005443415,0.00003977987,0.0001192848,0.0002555412,0.0006132044,0.8559306,0.03250515,0.09547377,0.01425088,0.00006442395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02423705,0.0001517998,0.9717838,0.0002156387,0.00001954752,0.000136624,0.000295886,0.001779325,0.001380218],"genre_scores_gemma":[0.2378239,0.0002786291,0.7576227,0.0001383486,0.00006152817,0.0002486355,0.001381567,0.0003727624,0.002071931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002731234,"threshold_uncertainty_score":0.01444429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00427333096314046,"score_gpt":0.1920211782188112,"score_spread":0.1877478472556707,"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."}}