{"id":"https://openalex.org/W4414428090","doi":"https://doi.org/10.1145/3749166","title":"G <scp>uardrail</scp> : Automated Integrity Constraint Synthesis From Noisy Data","display_name":"G <scp>uardrail</scp> : Automated Integrity Constraint Synthesis From Noisy Data","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414428090","doi":"https://doi.org/10.1145/3749166"},"language":"en","primary_location":{"id":"doi:10.1145/3749166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749166","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","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/A5101728918","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0001-7680-2817"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7680-2817","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044493129","display_name":"Zhaoyu Wang","orcid":"https://orcid.org/0009-0009-6892-1264"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhaoyu Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0009-6892-1264","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072001009","display_name":"Zhenlan Ji","orcid":"https://orcid.org/0000-0003-3167-0480"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenlan Ji","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-3167-0480","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884078","display_name":"Zongjie Li","orcid":"https://orcid.org/0000-0002-9897-4086"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zongjie Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-9897-4086","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618741","display_name":"Ao Sun","orcid":"https://orcid.org/0009-0007-5369-624X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ao Sun","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0007-5369-624X","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328264","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0866-0308"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-0866-0308","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12916854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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/T11719","display_name":"Data Quality and Management","score":0.9919999837875366,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/data-integrity","display_name":"Data integrity","score":0.717199981212616},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5698999762535095},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.541700005531311},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.4271000027656555},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4223000109195709},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.717199981212616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.4271000027656555},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C98199447","wikidata":"https://www.wikidata.org/wiki/Q2445044","display_name":"Materialized view","level":4,"score":0.33149999380111694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3749166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749166","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","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":43,"referenced_works":["https://openalex.org/W602497127","https://openalex.org/W1489843519","https://openalex.org/W1984566373","https://openalex.org/W2065000833","https://openalex.org/W2078132546","https://openalex.org/W2081186682","https://openalex.org/W2096713153","https://openalex.org/W2102489964","https://openalex.org/W2113607096","https://openalex.org/W2132525863","https://openalex.org/W2146908974","https://openalex.org/W2170712852","https://openalex.org/W2190899134","https://openalex.org/W2266772167","https://openalex.org/W2295468252","https://openalex.org/W2612824201","https://openalex.org/W2626990892","https://openalex.org/W2784560833","https://openalex.org/W2790634852","https://openalex.org/W2900091806","https://openalex.org/W2913790076","https://openalex.org/W2943955885","https://openalex.org/W2953054522","https://openalex.org/W3015276915","https://openalex.org/W3015738839","https://openalex.org/W3030026364","https://openalex.org/W3030496122","https://openalex.org/W3031504748","https://openalex.org/W3088135204","https://openalex.org/W3103264664","https://openalex.org/W3105239039","https://openalex.org/W3123228431","https://openalex.org/W3166632383","https://openalex.org/W3174922609","https://openalex.org/W4229675450","https://openalex.org/W4235951092","https://openalex.org/W4245234767","https://openalex.org/W4254182148","https://openalex.org/W4284701600","https://openalex.org/W4382202749","https://openalex.org/W4385568252","https://openalex.org/W4396571411","https://openalex.org/W4401856724"],"related_works":[],"abstract_inverted_index":{"Data":[0],"quality":[1],"issues":[2],"have":[3],"been":[4],"a":[5,34,85,92,95],"long-standing":[6],"challenge":[7],"in":[8,21,66,108,191],"the":[9,24,27,46,67,109,123,128,132,135,140,145,150,169,192,199,204,209],"database":[10],"community.":[11],"Erroneous":[12],"data":[13,47,129],"can":[14,55,100,173],"lead":[15],"to":[16,38,48,63,73,103,130,176,185,211],"incorrect":[17],"query":[18],"results,":[19],"which":[20],"turn":[22],"affect":[23],"credibility":[25],"of":[26,88,113,127,134,152,189],"data-driven":[28],"decisions.":[29],"To":[30,148],"circumvent":[31],"this":[32,81],"issue,":[33],"common":[35],"practice":[36],"is":[37,206],"discovery":[39],"integrity":[40,89,171],"constraints":[41,57,90,172],"and":[42,105,143,203],"enforce":[43],"them":[44,76],"on":[45,158],"ensure":[49],"its":[50],"quality.":[51],"For":[52],"instance,":[53],"one":[54],"use":[56,212],"entailed":[58],"by":[59],"functional":[60],"dependencies":[61],"(FDs)":[62],"detect":[64,104],"violations":[65],"data.":[68,79,110],"However,":[69],"existing":[70],"approaches":[71],"fail":[72],"effectively":[74],"discover":[75],"from":[77],"noisy":[78],"In":[80],"paper,":[82],"we":[83,115,155,166],"present":[84],"novel":[86],"form":[87],"as":[91],"program":[93,136],"under":[94],"domain-specific":[96],"language":[97],"(DSL)":[98],"that":[99,121,137,168],"be":[101,174],"used":[102,175],"rectify":[106],"errors":[107],"On":[111],"top":[112],"DSL,":[114],"propose":[116],"an":[117,186],"efficient":[118],"synthesis":[119,146],"algorithm":[120],"leverages":[122],"statistical":[124],"structural":[125],"properties":[126],"generate":[131],"sketch":[133],"significantly":[138],"reduces":[139],"search":[141],"space":[142],"speedup":[144],"process.":[147],"demonstrate":[149],"usefulness":[151],"our":[153],"approach,":[154],"evaluate":[156],"it":[157],"12":[159],"real-world":[160],"datasets":[161],"for":[162,208],"error":[163,193],"detection.":[164],"Then,":[165],"show":[167],"synthesized":[170],"solidify":[177],"ML-integrated":[178],"SQL":[179],"queries":[180],"over":[181],"48":[182],"queries,":[183],"leading":[184],"average":[187],"reduction":[188],"87%":[190],"rates.":[194],"Our":[195],"open-source":[196],"artifact,":[197],"including":[198],"G":[200],"uardrail":[201],"framework":[202],"datasets,":[205],"available":[207],"community":[210],"[2].":[213]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}