{"id":"https://openalex.org/W7170134852","doi":"https://doi.org/10.48550/arxiv.2607.20165","title":"Extending GouDa: Generation of Universal Datasets with (and without) Errors for Data Quality Benchmarking","display_name":"Extending GouDa: Generation of Universal Datasets with (and without) Errors for Data Quality Benchmarking","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170134852","doi":"https://doi.org/10.48550/arxiv.2607.20165"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.20165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.20165","pdf_url":"https://arxiv.org/pdf/2607.20165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.20165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052582753","display_name":"Valerie Restat","orcid":"https://orcid.org/0000-0002-5960-5886","observed_orcids":["https://orcid.org/0000-0002-5960-5886"]},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Restat, Valerie","raw_affiliation_strings":["Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075697602","display_name":"Andr\u00e9 Conrad","orcid":"https://orcid.org/0000-0001-6681-2798","observed_orcids":["https://orcid.org/0000-0001-6681-2798"]},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Conrad, Andr\u00e9","raw_affiliation_strings":["Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119360128","display_name":"Kevin M. Kramer","orcid":"https://orcid.org/0009-0003-7595-532X","observed_orcids":["https://orcid.org/0009-0003-7595-532X"]},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kramer, Kevin M.","raw_affiliation_strings":["Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004678152","display_name":"Uta St\u00f6rl","orcid":"https://orcid.org/0000-0003-2771-142X","observed_orcids":["https://orcid.org/0000-0003-2771-142X"]},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"St\u00f6rl, Uta","raw_affiliation_strings":["Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Computer Science , FernUniversit\u00e4t in Hagen , Hagen , Germany","institution_ids":["https://openalex.org/I120691247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I120691247"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9961000084877014,"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":0.9961000084877014,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.925000011920929},{"id":"https://openalex.org/keywords/gouda","display_name":"Gouda","score":0.8270000219345093},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.718999981880188},{"id":"https://openalex.org/keywords/ground-truth-generation","display_name":"ground truth generation","score":0.8619999885559082},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.8629999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566999793052673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6439999938011169},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6385999917984009},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5949000120162964},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C1232282","wikidata":"https://www.wikidata.org/wiki/Q1783551","display_name":"Data conversion","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C78168278","wikidata":"https://www.wikidata.org/wiki/Q5227269","display_name":"Data cube","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.20165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.20165","pdf_url":"https://arxiv.org/pdf/2607.20165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.20165","doi":"https://doi.org/10.48550/arxiv.2607.20165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.20165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.20165","pdf_url":"https://arxiv.org/pdf/2607.20165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7170134852.pdf","grobid_xml":"https://content.openalex.org/works/W7170134852.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4281401329","https://openalex.org/W7167464837","https://openalex.org/W2163190310","https://openalex.org/W7203872935","https://openalex.org/W4414943840","https://openalex.org/W7065930696","https://openalex.org/W7140030102","https://openalex.org/W4383987205","https://openalex.org/W3028701087","https://openalex.org/W7202262186"],"abstract_inverted_index":{"Synthetic":[0],"data":[1,9,11,26,35,40,73,84,93,101,115,151],"is":[2,27,74,79,111],"extremely":[3],"important":[4],"in":[5,23],"areas":[6],"such":[7,86],"as":[8,43,45,87],"quality,":[10],"cleaning,":[12],"and":[13,63,123,134],"machine":[14],"learning.":[15],"It":[16,55],"enables":[17,117],"the":[18,49,65,72,118,135,147],"analysis":[19],"of":[20,71,121,130,142,149],"use":[21,156],"cases":[22],"which":[24],"real":[25],"insufficient,":[28],"unavailable,":[29],"or":[30],"distorted.":[31],"However,":[32],"generating":[33],"synthetic":[34],"also":[36,91],"presents":[37],"challenges:":[38],"The":[39],"must":[41,56],"be":[42,57],"realistic":[44,150],"possible,":[46],"but":[47,90],"at":[48,64],"same":[50,66],"time":[51],"cover":[52],"edge":[53],"cases.":[54,157],"possible":[58,143],"to":[59,81,137],"insert":[60],"controlled":[61,119],"errors,":[62,122],"time,":[67],"an":[68],"error-free":[69],"version":[70],"usually":[75],"required.":[76],"Additionally,":[77],"it":[78,110],"necessary":[80],"consider":[82],"numerous":[83],"formats,":[85,116],"tabular":[88],"data,":[89],"NoSQL":[92],"models.":[94],"To":[95],"this":[96],"end,":[97],"we":[98],"present":[99],"our":[100],"generator":[102],"GouDa.":[103],"GouDa":[104],"precisely":[105],"meets":[106],"these":[107],"requirements":[108],"-":[109],"suitable":[112],"for":[113],"different":[114,131,155],"insertion":[120],"generates":[124],"ground":[125],"truth.":[126],"A":[127],"wide":[128],"range":[129],"generation":[132,148],"functions":[133],"option":[136],"add":[138],"your":[139],"own":[140],"lists":[141],"attribute":[144],"values":[145],"allow":[146],"that":[152],"covers":[153],"many":[154]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-24T00:00:00"}