{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00439759,0.0009174236,0.002178551,0.005131835,0.001949731,0.004069827,0.003392497,0.001951023,0.005277407],"category_scores_gemma":[0.028504,0.0009309381,0.002537436,0.01051983,0.001648884,0.009212591,0.004871484,0.001543815,0.001107816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00163729,"about_ca_system_score_gemma":0.002807291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006355432,"about_ca_topic_score_gemma":0.006847159,"domain_scores_codex":[0.9944501,0.001424897,0.0005030108,0.001389422,0.001759829,0.000472753],"domain_scores_gemma":[0.982085,0.01225082,0.001197078,0.002703825,0.001291914,0.0004713486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008764245,0.0005574672,0.01557208,0.001270303,0.0004438231,0.001172553,0.00131813,0.4051214,0.004733785,0.1075455,0.0332072,0.4281812],"study_design_scores_gemma":[0.00009483257,0.0001152409,0.001094164,0.0001117102,0.00009716157,0.0004965825,0.0005219899,0.8407168,0.004185756,0.142105,0.01041955,0.00004125666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08211512,0.002759091,0.8976465,0.001390047,0.0001406111,0.000336657,0.004987122,0.005803411,0.004821426],"genre_scores_gemma":[0.3087517,0.0007467618,0.6779891,0.0004006174,0.00009948557,0.0003581535,0.008297247,0.0005445703,0.002812491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006355432,"threshold_uncertainty_score":0.02325696,"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."}}