{"id":"W2798664493","doi":"10.14778/3192965.3192973","title":"Table union search on open data","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Computer science; Benchmark (surveying); Data mining; Set (abstract data type); Semantic search; Domain (mathematical analysis); Ontology; Decision table; Probabilistic logic; Information retrieval; Search engine; Artificial intelligence; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01025841,0.0001084626,0.000195496,0.0001102498,0.0002647666,0.0006400906,0.01024161,0.00002553353,0.0004610213],"category_scores_gemma":[0.001331878,0.00006089952,0.0000335905,0.0007900212,0.0002026631,0.001010727,0.01295218,0.0001049761,0.0004453454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003409791,"about_ca_system_score_gemma":0.00004092453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004345713,"about_ca_topic_score_gemma":0.00004147274,"domain_scores_codex":[0.9969523,0.0000432489,0.0004378641,0.000614234,0.001692751,0.0002595937],"domain_scores_gemma":[0.9979764,0.000156895,0.0002506188,0.001158114,0.0003871694,0.00007080311],"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":[0.00007519912,0.0002059809,0.0009332173,0.00001290875,0.00002840523,1.563479e-7,0.0004069704,0.000003335607,0.002379407,0.1044471,0.8579091,0.0335983],"study_design_scores_gemma":[0.000430178,0.0002302428,0.001860879,0.00006300217,0.0000130843,0.00000114046,0.001742479,0.0004170132,0.04895037,0.02350083,0.922684,0.000106814],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1439259,0.00005370688,0.0005731527,0.06921851,0.001668451,0.002985392,0.0004888851,0.0000736525,0.7810124],"genre_scores_gemma":[0.9754143,0.00002897564,0.001730507,0.003336686,0.0001356275,0.00002306954,0.00001300143,0.00001198877,0.01930586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8314884,"threshold_uncertainty_score":0.9951134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4805425545209558,"score_gpt":0.4884253644300699,"score_spread":0.007882809909114052,"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."}}