{"id":"W2972941956","doi":"10.1109/tkde.2019.2940019","title":"Bayesian Networks for Data Integration in the Absence of Foreign Keys","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Relational database; Probabilistic logic; Inference; Data integration; Bayesian network; Data mining; Cardinality (data modeling); Relation (database); Population; Theoretical computer science; Data science; Information retrieval; Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002672862,0.0000928476,0.0001553471,0.0001670503,0.00004818495,0.00009553989,0.001574334,0.00004136442,0.00002824515],"category_scores_gemma":[0.00009193257,0.00006370349,0.00002292748,0.0003886991,0.00002134587,0.0008133609,0.00002759897,0.0001244935,0.00001605637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007877881,"about_ca_system_score_gemma":0.00001385602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002776294,"about_ca_topic_score_gemma":0.0002893638,"domain_scores_codex":[0.998862,0.00004984558,0.0003455468,0.0004014504,0.0002082736,0.0001328729],"domain_scores_gemma":[0.9968945,0.001126152,0.00005092088,0.001862587,0.00003853228,0.00002729421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001097045,0.0004099306,0.0001682927,0.0001780828,0.00006214937,0.000001913362,0.001648511,0.1429623,0.0004143418,0.01622117,0.01499689,0.8228267],"study_design_scores_gemma":[0.0002434138,0.00004682169,0.0002072163,0.00005513913,0.00001175586,0.000001127935,0.000621536,0.9838045,0.0001318168,0.0003993438,0.01439507,0.00008225713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001230318,0.0001197867,0.9968024,0.00007699007,0.0003507523,0.0003518455,0.0005194247,0.00001330636,0.0005351476],"genre_scores_gemma":[0.9966311,0.00007915783,0.00286607,0.00003710439,0.00003175615,0.00001673263,0.0001965039,0.000006575117,0.0001349577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9954008,"threshold_uncertainty_score":0.2925531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1235244620639133,"score_gpt":0.3687156893233667,"score_spread":0.2451912272594534,"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."}}