{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000279649,0.0001109785,0.0001331596,0.0001075928,0.00007544364,0.000125627,0.001261974,0.00002792154,0.000006379492],"category_scores_gemma":[0.0000333598,0.0000660921,0.00004452606,0.0003760054,0.00008179904,0.001309423,0.0004368185,0.0001165472,0.000001447988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000012318,"about_ca_system_score_gemma":0.0000168221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004070364,"about_ca_topic_score_gemma":0.000002296309,"domain_scores_codex":[0.9990391,0.000002612188,0.0002448828,0.0001369166,0.0004125193,0.0001639565],"domain_scores_gemma":[0.9992526,0.00001444592,0.0003580128,0.0001959817,0.0001465543,0.00003241092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000621849,0.00008510726,0.007225795,0.0004591264,0.0001445296,3.430291e-7,0.003317973,0.0001761496,0.1251629,0.7756984,0.001619018,0.08604848],"study_design_scores_gemma":[0.00246747,0.0002636164,0.01019223,0.0002166417,0.00008428915,0.00002185269,0.0007204661,0.01667423,0.9236752,0.0260879,0.01913372,0.0004624089],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9696986,0.00001918275,0.0211526,0.001596953,0.0005382145,0.0007217533,0.00001011467,0.0001086945,0.006153862],"genre_scores_gemma":[0.9006141,0.000003851063,0.09922139,0.00007125617,0.00002750874,0.00001287462,0.000001191046,0.000003826257,0.00004403491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7985122,"threshold_uncertainty_score":0.2695158,"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."}}