{"id":"https://openalex.org/W4414266941","doi":"https://doi.org/10.14778/3750601.3750651","title":"Can Surrogate Keys Negatively Impact Data Quality?","display_name":"Can Surrogate Keys Negatively Impact Data Quality?","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414266941","doi":"https://doi.org/10.14778/3750601.3750651"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750651","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750651","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029884401","display_name":"Mathilde Marcy","orcid":null},"institutions":[{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I4210155607","display_name":"Laboratoire d'Informatique en Images et Syst\u00e8mes d'Information","ror":"https://ror.org/04dv4he91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I112936343","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210155607","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mathilde Marcy","raw_affiliation_strings":["INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France"],"affiliations":[{"raw_affiliation_string":"INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France","institution_ids":["https://openalex.org/I48430043","https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210155607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064659680","display_name":"Jean-Marc Petit","orcid":"https://orcid.org/0000-0002-0015-745X"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210155607","display_name":"Laboratoire d'Informatique en Images et Syst\u00e8mes d'Information","ror":"https://ror.org/04dv4he91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I112936343","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210155607","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Marc Petit","raw_affiliation_strings":["INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France"],"affiliations":[{"raw_affiliation_string":"INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France","institution_ids":["https://openalex.org/I48430043","https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210155607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063350327","display_name":"Vasile-Marian Scuturici","orcid":"https://orcid.org/0000-0001-8139-0212"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I4210155607","display_name":"Laboratoire d'Informatique en Images et Syst\u00e8mes d'Information","ror":"https://ror.org/04dv4he91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I112936343","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210155607","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vasile-Marian Scuturici","raw_affiliation_strings":["INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France"],"affiliations":[{"raw_affiliation_string":"INSA Lyon, CNRS, UCBL, LIRIS, Villeurbanne, France","institution_ids":["https://openalex.org/I48430043","https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210155607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019970103","display_name":"Jocelyn Bonjour","orcid":"https://orcid.org/0000-0001-7773-6073"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104752","display_name":"Centre d'\u00c9nerg\u00e9tique et de Thermique de Lyon","ror":"https://ror.org/01k383v05","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210095849","https://openalex.org/I4210104752","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jocelyn Bonjour","raw_affiliation_strings":["INSA Lyon, CNRS, CETHIL, Villeurbanne, France"],"affiliations":[{"raw_affiliation_string":"INSA Lyon, CNRS, CETHIL, Villeurbanne, France","institution_ids":["https://openalex.org/I4210104752","https://openalex.org/I48430043","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079453442","display_name":"Camille Fertel","orcid":null},"institutions":[{"id":"https://openalex.org/I86908984","display_name":"University of French Polynesia","ror":"https://ror.org/03ay59x86","country_code":"PF","type":"education","lineage":["https://openalex.org/I86908984"]}],"countries":["PF"],"is_corresponding":false,"raw_author_name":"Camille Fertel","raw_affiliation_strings":["CEMAFROID, Fresnes, France"],"affiliations":[{"raw_affiliation_string":"CEMAFROID, Fresnes, France","institution_ids":["https://openalex.org/I86908984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008761165","display_name":"G Cavalier","orcid":null},"institutions":[{"id":"https://openalex.org/I86908984","display_name":"University of French Polynesia","ror":"https://ror.org/03ay59x86","country_code":"PF","type":"education","lineage":["https://openalex.org/I86908984"]}],"countries":["PF"],"is_corresponding":false,"raw_author_name":"Gerald Cavalier","raw_affiliation_strings":["CEMAFROID, Fresnes, France"],"affiliations":[{"raw_affiliation_string":"CEMAFROID, Fresnes, France","institution_ids":["https://openalex.org/I86908984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029884401"],"corresponding_institution_ids":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I4210155607","https://openalex.org/I48430043"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30752108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"12","first_page":"5279","last_page":"5282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5892999768257141},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.5609999895095825},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.46299999952316284},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4334999918937683},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.40720000863075256},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.3617999851703644},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.32839998602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31630000472068787},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C48947383","wikidata":"https://www.wikidata.org/wiki/Q830719","display_name":"Visitor pattern","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C70236469","wikidata":"https://www.wikidata.org/wiki/Q1078262","display_name":"Database administrator","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750651","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750651","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1571341547","https://openalex.org/W1994962776","https://openalex.org/W4220923188","https://openalex.org/W4242744113"],"related_works":[],"abstract_inverted_index":{"Surrogate":[0],"keys":[1,11,51,64,93,148],"are":[2,16,25,79,131],"now":[3],"extensively":[4],"utilized":[5],"by":[6],"database":[7,67],"designers":[8],"to":[9,19,72,83,133,187,255,290],"implement":[10],"in":[12,232],"SQL":[13,278],"tables.":[14],"They":[15],"straightforward,":[17],"easy":[18],"understand,":[20],"enable":[21],"efficient":[22],"access,":[23],"and":[24,114,138,287],"often":[26],"considered":[27],"a":[28,102,160,199,210,237,241,245,269],"sufficient":[29],"guarantee":[30],"of":[31,42,97,105,122,180,201,213,229,265,294],"data":[32,55,126,136,242,270],"integrity":[33],"despite":[34],"lacking":[35],"any":[36],"real-world":[37],"semantic":[38],"meaning.":[39],"In":[40,89,119,194],"spite":[41],"all":[43],"their":[44],"benefits,":[45],"one":[46,228],"might":[47],"wonder":[48],"whether":[49],"surrogate":[50,63,92,147],"can":[52,108,225],"negatively":[53],"impact":[54],"quality.":[56],"IT":[57],"developers":[58],"who":[59],"rely":[60],"exclusively":[61],"on":[62,178,209,227],"when":[65],"designing":[66],"schemas":[68],"may":[69],"be":[70,109],"tempted":[71],"not":[73],"encode":[74],"natural":[75,151,257],"keys,":[76,113,152,258],"as":[77,81],"they":[78],"perceived":[80],"complex":[82,103],"manage":[84],"at":[85],"the":[86,95,120,172,189,202,214,221,223,233,285,292,295],"application":[87],"level.":[88],"such":[90],"settings,":[91],"allow":[94],"presence":[96,121],"so-called":[98],"artificial":[99,123],"unicity":[100],",":[101],"form":[104],"redundancy":[106,166],"that":[107],"propagated":[110],"through":[111,191,205],"foreign":[112],"other":[115],"underlying":[116],"data-quality":[117],"issues.":[118],"unicity,":[124],"most":[125],"cleaning":[127],"techniques,":[128],"especially":[129],"unsupervised,":[130],"likely":[132],"fail,":[134],"making":[135],"preparation":[137],"analytics":[139],"very":[140,262],"challenging.":[141],"For":[142],"relational":[143],"databases":[144,289],"implemented":[145,177],"with":[146,251],"but":[149],"no":[150],"we":[153,197],"developed":[154],"RED2Hunt":[155,203],"(RElational":[156],"Databases":[157],"REDundancy":[158],"Hunting),":[159],"human-in-the-loop":[161],"framework":[162,175],"for":[163,253],"identifying":[164],"hidden":[165],"and,":[167],"if":[168],"problems":[169],"occur,":[170],"clean":[171],"database.":[173,219],"The":[174],"was":[176],"top":[179],"PostgreSQL":[181],"within":[182],"an":[183],"eponym":[184],"web-based":[185],"platform":[186],"guide":[188],"expert":[190,239],"its":[192],"application.":[193],"this":[195],"paper,":[196],"present":[198],"demonstration":[200],"tool":[204],"three":[206],"interactive":[207],"scenarios":[208],"polluted":[211],"instance":[212],"publicly":[215],"available":[216],"Perfect":[217,234],"Pet":[218,235],"During":[220],"demonstration,":[222],"visitor":[224],"take":[226],"two":[230,275],"roles":[231],"database:":[236],"domain":[238,246],"or":[240,280],"scientist.":[243],"As":[244,268],"expert,":[247],"she":[248,272],"will":[249,273],"interact":[250],"RED2Hunt,":[252],"example":[254],"elicit":[256],"from":[259],"simple":[260,276],"yet":[261],"intuitive":[263],"visualizations":[264],"tables'":[266],"attributes.":[267],"scientist,":[271],"explore":[274],"scenarios\u2014executing":[277],"queries":[279],"applying":[281],"learning":[282],"models\u2014on":[283],"both":[284],"initial":[286],"cleaned":[288],"grasp":[291],"benefits":[293],"approach.":[296]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
