{"id":"W2238711864","doi":"10.1561/9781680830231","title":"Trends in Cleaning Relational Data: Consistency and Deduplication","year":2015,"lang":"en","type":"book","venue":"now publishers, Inc. eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data quality; Computer science; Data deduplication; Data integrity; Relational database; Consistency (knowledge bases); Anomaly detection; Data consistency; Data mining; Data science; Automation; Process (computing); Data warehouse; Database; Quality (philosophy); Artificial intelligence; Engineering","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009891309,0.0003277012,0.0005639128,0.001447126,0.000164106,0.002311692,0.002215031,0.0004410967,0.0005017726],"category_scores_gemma":[0.002069721,0.0002990439,0.00006239859,0.000273134,0.0003509328,0.003096117,0.002120657,0.0006385488,0.0002878115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002816413,"about_ca_system_score_gemma":0.0007819736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001267242,"about_ca_topic_score_gemma":0.002289442,"domain_scores_codex":[0.9944764,0.000291083,0.001278286,0.001438176,0.002177205,0.0003388049],"domain_scores_gemma":[0.9951984,0.0008436409,0.0007438368,0.002504645,0.0004741026,0.0002353605],"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":[0.00001530237,0.00001580691,0.0001243378,0.000009608429,0.00002268146,0.000006855809,0.0002035218,0.000001950162,2.34588e-7,0.06580677,0.7366928,0.1971001],"study_design_scores_gemma":[0.0004483171,0.00002746318,0.001218245,0.00004694225,0.00003622905,0.00000620665,0.0003363875,0.0003578584,1.554054e-7,0.102589,0.8946401,0.0002930168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00004478248,0.000347872,0.0004044535,0.001565067,0.0006189618,0.0002834307,0.0006484935,0.00006980323,0.9960172],"genre_scores_gemma":[0.0009272893,0.000008588653,0.001944587,0.001139004,0.0003445107,0.00002918406,0.008147668,0.00003770042,0.9874215],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.196807,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3277735594755778,"score_gpt":0.4006223382773515,"score_spread":0.07284877880177365,"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."}}