{"id":"https://openalex.org/W4411528132","doi":"https://doi.org/10.1145/3735654.3735939","title":"Towards Automated Task-Aware Data Validation","display_name":"Towards Automated Task-Aware Data Validation","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411528132","doi":"https://doi.org/10.1145/3735654.3735939"},"language":"en","primary_location":{"id":"doi:10.1145/3735654.3735939","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735939","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735939","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086037981","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0004-1887-6630"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0004-1887-6630","affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13539113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.7878400087356567},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5705514550209045},{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.4226493835449219},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2000361680984497},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09815877676010132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878400087356567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5705514550209045},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.4226493835449219},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2000361680984497},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09815877676010132},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3735654.3735939","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735939","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735939","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:doi:10.14279/depositonce-24549","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":{"id":"doi:10.1145/3735654.3735939","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735939","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735939","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411528132.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2544486974","https://openalex.org/W2612744932","https://openalex.org/W2798323405","https://openalex.org/W2889249015","https://openalex.org/W2929941791","https://openalex.org/W2946595616","https://openalex.org/W3030026364","https://openalex.org/W3045754299","https://openalex.org/W3105684693","https://openalex.org/W3105977086","https://openalex.org/W3166632383","https://openalex.org/W3216644311","https://openalex.org/W4320165837","https://openalex.org/W4385568252","https://openalex.org/W4387848581","https://openalex.org/W4399776857"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"is":[1,13,33],"a":[2,23,50,77,109],"central":[3],"resource":[4],"for":[5,15,100,129,161],"modern":[6],"enterprises":[7],"and":[8,10,84,96,127,154,172],"institutions,":[9],"data":[11,29,54,64,89,94,101,136,148,156,166],"validation":[12,55],"essential":[14],"ensuring":[16],"the":[17,37,41,45,69,131,147,162],"reliability":[18],"of":[19,26,40,71,122,133,165],"downstream":[20,72,115,152],"applications.":[21],"However,":[22],"major":[24],"limitation":[25],"existing":[27],"automated":[28],"unit":[30,65,102,157],"testing":[31],"frameworks":[32],"that":[34,43,56,80,140,159],"they":[35],"ignore":[36],"specific":[38],"requirements":[39],"tasks":[42,116,153],"consume":[44],"data.":[46],"This":[47],"paper":[48],"introduces":[49],"task-aware":[51],"approach":[52],"to":[53,61,87],"leverages":[57],"large":[58],"language":[59],"models":[60],"generate":[62],"customized":[63],"tests":[66,158],"based":[67],"on":[68],"semantics":[70],"code.":[73],"We":[74,104,138,168],"present":[75],"tadv,":[76],"prototype":[78,107,173],"system":[79],"analyzes":[81],"task":[82],"code":[83,99,174],"dataset":[85],"profiles":[86],"identify":[88],"access":[90,125],"patterns,":[91],"infer":[92],"implicit":[93],"assumptions,":[95],"produce":[97],"executable":[98],"tests.":[103],"evaluate":[105],"our":[106,170],"with":[108],"novel":[110],"benchmark":[111,171],"comprising":[112],"over":[113],"100":[114],"across":[117],"two":[118],"datasets,":[119],"including":[120],"annotations":[121],"their":[123],"column":[124],"patterns":[126],"support":[128],"assessing":[130],"impact":[132,164],"synthetically":[134],"injected":[135],"errors.":[137,167],"demonstrate":[139],"tadv":[141],"outperforms":[142],"task-agnostic":[143],"baselines":[144],"in":[145],"detecting":[146],"columns":[149],"accessed":[150],"by":[151],"generating":[155],"account":[160],"end-to-end":[163],"make":[169],"publicly":[175],"available.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}