{"id":"W2189052568","doi":"10.14778/2850583.2850586","title":"The iBench integration metadata generator","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Metadata; Computer science; Schema evolution; Data integration; Generality; Schema (genetic algorithms); Generator (circuit theory); Data mapping; Data element; Data science; Information retrieval; Data mining; Database; World Wide Web; Database schema","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":[0.007019219,0.0001130564,0.0001636045,0.00006507192,0.0002354384,0.0007553889,0.002256308,0.00002745744,0.0000224907],"category_scores_gemma":[0.003664513,0.00004769289,0.00009430647,0.000526696,0.0001357436,0.0008420558,0.001008352,0.00009884471,0.00007023685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006292882,"about_ca_system_score_gemma":0.00004506459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008917267,"about_ca_topic_score_gemma":0.0000510449,"domain_scores_codex":[0.9971278,0.00004087767,0.0005591958,0.0002971171,0.001778651,0.0001964142],"domain_scores_gemma":[0.9982618,0.0001895725,0.0004106837,0.0004631054,0.0005876063,0.00008720911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000386903,0.00007532341,0.0004358903,0.000005769461,0.0000460658,1.272013e-7,0.001005157,0.00001120344,0.004470577,0.4131789,0.5342453,0.04648698],"study_design_scores_gemma":[0.0003684557,0.00007872825,0.0006366902,0.00001771285,0.00004270734,0.000002437791,0.008432384,0.0005202109,0.07559018,0.137713,0.7764785,0.0001189246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.56227,0.003211478,0.01268814,0.1451318,0.01012563,0.005502163,0.0003156883,0.0002648266,0.2604903],"genre_scores_gemma":[0.9827819,0.0000670096,0.001829781,0.0008036694,0.0001528789,0.00007074004,0.000004070435,0.000008888826,0.014281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.420512,"threshold_uncertainty_score":0.7284233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2684436286050799,"score_gpt":0.3942632791998347,"score_spread":0.1258196505947548,"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."}}