{"id":"https://openalex.org/W2947965780","doi":"https://doi.org/10.1186/s40537-019-0204-5","title":"Diftong: a tool for validating big data workflows","display_name":"Diftong: a tool for validating big data workflows","publication_year":2019,"publication_date":"2019-05-18","ids":{"openalex":"https://openalex.org/W2947965780","doi":"https://doi.org/10.1186/s40537-019-0204-5","mag":"2947965780"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-019-0204-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0204-5","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0204-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0204-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044461578","display_name":"Raya Rizk","orcid":"https://orcid.org/0000-0003-1150-3503"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Raya Rizk","raw_affiliation_strings":["Department of Informatics and Media, Uppsala University, Kyrkog\u00e5dsgatan 10, 753 13, Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Media, Uppsala University, Kyrkog\u00e5dsgatan 10, 753 13, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027129096","display_name":"Steve McKeever","orcid":"https://orcid.org/0000-0002-1970-2884"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Steve McKeever","raw_affiliation_strings":["Department of Informatics and Media, Uppsala University, Kyrkog\u00e5dsgatan 10, 753 13, Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Media, Uppsala University, Kyrkog\u00e5dsgatan 10, 753 13, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111508410","display_name":"Johan Petrini","orcid":null},"institutions":[{"id":"https://openalex.org/I1307248880","display_name":"Swedish National Bank","ror":"https://ror.org/01n28jn45","country_code":"SE","type":"other","lineage":["https://openalex.org/I1307248880"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Johan Petrini","raw_affiliation_strings":["Klarna Bank AB, Sveav\u00e4gen 46, 111 34, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Klarna Bank AB, Sveav\u00e4gen 46, 111 34, Stockholm, Sweden","institution_ids":["https://openalex.org/I1307248880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034985100","display_name":"Erik Zeitler","orcid":null},"institutions":[{"id":"https://openalex.org/I1307248880","display_name":"Swedish National Bank","ror":"https://ror.org/01n28jn45","country_code":"SE","type":"other","lineage":["https://openalex.org/I1307248880"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erik Zeitler","raw_affiliation_strings":["Klarna Bank AB, Sveav\u00e4gen 46, 111 34, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Klarna Bank AB, Sveav\u00e4gen 46, 111 34, Stockholm, Sweden","institution_ids":["https://openalex.org/I1307248880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044461578"],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.8232,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76536804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8870018124580383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8514044284820557},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7416083812713623},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.5845395922660828},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.533359706401825},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5173644423484802},{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.48401638865470886},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4822845757007599},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4765399098396301},{"id":"https://openalex.org/keywords/turnaround-time","display_name":"Turnaround time","score":0.4274807572364807},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41570845246315},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3667319416999817},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16755560040473938}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8870018124580383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514044284820557},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7416083812713623},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.5845395922660828},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.533359706401825},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5173644423484802},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.48401638865470886},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4822845757007599},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4765399098396301},{"id":"https://openalex.org/C176553487","wikidata":"https://www.wikidata.org/wiki/Q7855819","display_name":"Turnaround time","level":2,"score":0.4274807572364807},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41570845246315},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3667319416999817},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16755560040473938},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s40537-019-0204-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0204-5","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0204-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:DiVA.org:uu-385328","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-385328","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article in journal"},{"id":"pmh:oai:doaj.org/article:b5772659c60d4748a8ee10ce0fc1e910","is_oa":true,"landing_page_url":"https://doaj.org/article/b5772659c60d4748a8ee10ce0fc1e910","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 6, Iss 1, Pp 1-27 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-019-0204-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-019-0204-5","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0204-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324119","display_name":"Uppsala Universitet","ror":"https://ror.org/048a87296"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947965780.pdf","grobid_xml":"https://content.openalex.org/works/W2947965780.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W935072310","https://openalex.org/W1491282455","https://openalex.org/W1506215767","https://openalex.org/W1534422116","https://openalex.org/W1775123915","https://openalex.org/W1993892970","https://openalex.org/W2078704774","https://openalex.org/W2118023920","https://openalex.org/W2280934013","https://openalex.org/W2316007180","https://openalex.org/W2341832822","https://openalex.org/W2407969335","https://openalex.org/W2475898698","https://openalex.org/W2492590231","https://openalex.org/W2501376531","https://openalex.org/W2509656895","https://openalex.org/W2528861271","https://openalex.org/W2600197702","https://openalex.org/W2625373267","https://openalex.org/W2725944869","https://openalex.org/W2773981895","https://openalex.org/W2806774288","https://openalex.org/W2884466623","https://openalex.org/W2895112601","https://openalex.org/W2897564881","https://openalex.org/W2898879451","https://openalex.org/W4243982364"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W1992029172","https://openalex.org/W2605582854","https://openalex.org/W4309344469","https://openalex.org/W2291191244","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W2613195858"],"abstract_inverted_index":{"Data":[0],"validation":[1,50,141],"is":[2,22,120],"about":[3],"verifying":[4],"the":[5,27,35,40,46,82,85,106,115,125,132,140],"correctness":[6],"of":[7,30,48,64,84,108,117,135,151],"data.":[8],"When":[9],"organisations":[10],"update":[11],"and":[12,44,69,75],"refine":[13],"their":[14,109],"data":[15,153],"transformations":[16],"to":[17,24,67,80,91,100,104,124],"meet":[18],"evolving":[19],"requirements,":[20],"it":[21,130],"imperative":[23],"ensure":[25],"that":[26,102],"new":[28],"version":[29],"a":[31,49,65,147],"workflow":[32,66],"still":[33],"produces":[34],"correct":[36],"output.":[37],"We":[38],"motivate":[39],"need":[41,103],"for":[42,139,146],"workflows":[43],"describe":[45],"implementation":[47],"tool":[51,55],"called":[52],"Diftong.":[53],"This":[54],"compares":[56],"two":[57],"tabular":[58],"databases":[59],"resulting":[60],"from":[61],"different":[62],"versions":[63],"detect":[68],"prevent":[70],"potential":[71],"unwanted":[72],"alterations.":[73],"Row-based":[74],"column-based":[76],"statistics":[77],"are":[78],"used":[79],"quantify":[81],"results":[83,94],"database":[86],"comparison.":[87],"Diftong":[88],"was":[89],"shown":[90],"provide":[92],"accurate":[93],"in":[95],"test":[96],"scenarios,":[97],"bringing":[98],"benefits":[99],"companies":[101],"validate":[105],"outputs":[107],"workflows.":[110,155],"By":[111],"automating":[112],"this":[113,144],"process,":[114],"risk":[116],"human":[118],"error":[119],"also":[121],"eliminated.":[122],"Compared":[123],"more":[126,148],"labour-intensive":[127],"manual":[128],"alternative,":[129],"has":[131],"added":[133],"benefit":[134],"improved":[136],"turnaround":[137],"time":[138],"process.":[142],"Together":[143],"allows":[145],"agile":[149],"way":[150],"updating":[152],"transformation":[154]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
