{"id":"https://openalex.org/W4404181258","doi":"https://doi.org/10.14778/3685800.3685878","title":"Rock: Cleaning Data with both ML and Logic Rules","display_name":"Rock: Cleaning Data with both ML and Logic Rules","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181258","doi":"https://doi.org/10.14778/3685800.3685878"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685878","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685878","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/A5023638404","display_name":"Zian Bao","orcid":"https://orcid.org/0009-0006-9899-653X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zian Bao","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114567571","display_name":"Binbin Bie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Bie","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070565287","display_name":"Wenfei Fan","orcid":"https://orcid.org/0000-0001-5149-2656"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenfei Fan","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China and University of Edinburgh, United Kingdom and Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China and University of Edinburgh, United Kingdom and Beihang University, China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044432298","display_name":"Daji Li","orcid":"https://orcid.org/0009-0003-2858-8483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daji Li","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967799","display_name":"Mengyun Li","orcid":"https://orcid.org/0009-0008-3488-7240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengyun Li","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032151145","display_name":"Kaiwen Lin","orcid":"https://orcid.org/0000-0002-0314-0653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiwen Lin","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069478199","display_name":"Peijie Liu","orcid":"https://orcid.org/0000-0002-1847-3952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peijie Liu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001973917","display_name":"Peng Liu","orcid":"https://orcid.org/0009-0001-3948-8985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055494376","display_name":"Zhicong Lv","orcid":"https://orcid.org/0009-0004-5746-724X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhicong Lv","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091815428","display_name":"Mingliang Ouyang","orcid":"https://orcid.org/0009-0009-1367-5465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingliang Ouyang","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101006590","display_name":"Chenyang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyang Sun","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102741279","display_name":"Shuai Tang","orcid":"https://orcid.org/0009-0004-7245-6258"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Tang","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068930286","display_name":"Yaoshu Wang","orcid":"https://orcid.org/0000-0002-5760-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoshu Wang","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103282522","display_name":"Qiyuan Wei","orcid":"https://orcid.org/0009-0008-2246-2923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiyuan Wei","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030966569","display_name":"Xiangqian Wu","orcid":"https://orcid.org/0000-0002-0956-8757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangqian Wu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070592593","display_name":"Min Xie","orcid":"https://orcid.org/0000-0002-8500-8364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Xie","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082794062","display_name":"Jing Zhang","orcid":"https://orcid.org/0009-0002-7236-5781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024129642","display_name":"Runxiao Zhao","orcid":"https://orcid.org/0009-0002-9157-2727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runxiao Zhao","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101433124","display_name":"Yilin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilin Zhu","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5023638404"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23976608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"12","first_page":"4373","last_page":"4376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9965000152587891,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3928847014904022},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.37114110589027405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3928847014904022},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.37114110589027405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685878","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685878","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1977041160","https://openalex.org/W2077518845","https://openalex.org/W2169940602","https://openalex.org/W2171332293","https://openalex.org/W3082197983","https://openalex.org/W3164439293","https://openalex.org/W4281879035","https://openalex.org/W4289533900","https://openalex.org/W4380433154","https://openalex.org/W4381621947"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2324615561","https://openalex.org/W2086120259","https://openalex.org/W2390279801","https://openalex.org/W2245170124","https://openalex.org/W2076393078","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"We":[0,72],"demonstrate":[1,74],"Rock,":[2],"a":[3,49],"system":[4],"for":[5,59,76,89],"cleaning":[6,84],"relational":[7],"data.":[8],"Rock":[9,75],"highlights":[10],"the":[11],"following":[12],"unique":[13],"features:":[14],"(1)":[15],"it":[16,36,54],"extends":[17],"logic":[18,33],"rules":[19],"by":[20],"embedding":[21],"machine":[22],"learning":[23],"models":[24],"as":[25],"predicates,":[26],"to":[27],"benefit":[28],"from":[29],"both":[30],"ML":[31],"and":[32,44,52,64,69,91,97,102],"deduction;":[34],"(2)":[35],"supports":[37],"entity":[38],"resolution,":[39,41],"conflict":[40],"timeliness":[42],"deduction":[43],"missing":[45],"data":[46],"imputation":[47],"in":[48,67],"unified":[50],"process;":[51],"(3)":[53],"provides":[55],"parallelly":[56],"scalable":[57],"algorithms":[58],"rule":[60],"discovery,":[61],"error":[62,65],"detection":[63],"correction,":[66],"batch":[68],"incremental":[70],"modes.":[71],"will":[73],"its":[77],"(a)":[78],"easy-to-use":[79],"interface,":[80],"(b)":[81],"scalability":[82],"when":[83],"large":[85],"datasets,":[86],"(c)":[87],"accuracy":[88],"detecting":[90],"correcting":[92],"errors":[93],"across":[94],"multiple":[95],"tables,":[96],"(d)":[98],"applications":[99],"at":[100],"banks":[101],"HR":[103],"departments.":[104]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
