{"id":"W4293582904","doi":"10.1561/1900000045","title":"Trends in Cleaning Relational Data: Consistency and Deduplication","year":2015,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Consistency (knowledge bases); Data consistency; Computer science; Database; Data science; Artificial intelligence","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":[],"category_scores_codex":[0.0005498747,0.0001128742,0.000130907,0.0008511615,0.0001079755,0.0001363608,0.003080752,0.00004488813,0.00002088301],"category_scores_gemma":[0.004119711,0.0001159431,0.000008157154,0.00125918,0.000154322,0.002621671,0.01980673,0.0001655999,0.000005283241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005339748,"about_ca_system_score_gemma":0.00004852975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004025544,"about_ca_topic_score_gemma":0.001707214,"domain_scores_codex":[0.9987189,0.00005485475,0.0002842902,0.0005888934,0.0001706793,0.0001823735],"domain_scores_gemma":[0.9957698,0.0002159813,0.00008642102,0.003832095,0.00003613821,0.00005959396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000007713028,0.0001312015,0.0831861,0.000007527317,0.00001149565,0.0000140904,0.0001297092,0.00001829974,0.00001198183,0.1558312,0.07004552,0.6906052],"study_design_scores_gemma":[0.001680598,0.00007316098,0.4506497,0.0001123375,0.0000192148,0.0001016617,0.00025361,0.3981661,0.00002694998,0.08449382,0.0639153,0.0005075329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2606678,0.00671396,0.5801293,0.1176315,0.001338761,0.0004932336,0.004134353,0.001670219,0.02722087],"genre_scores_gemma":[0.619036,0.0001274161,0.3763247,0.00006919898,0.00002476711,0.00002187645,0.004317646,0.000007336328,0.00007115418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6900976,"threshold_uncertainty_score":0.9881209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2018429451686717,"score_gpt":0.3689833687587856,"score_spread":0.1671404235901139,"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."}}