{"id":"https://openalex.org/W4398234736","doi":"https://doi.org/10.1145/3626246.3653372","title":"Rock: Cleaning Data by Embedding ML in Logic Rules","display_name":"Rock: Cleaning Data by Embedding ML in Logic Rules","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398234736","doi":"https://doi.org/10.1145/3626246.3653372"},"language":"en","primary_location":{"id":"doi:10.1145/3626246.3653372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-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/A5102918743","display_name":"Xianchun Bao","orcid":"https://orcid.org/0009-0001-2934-2616"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xianchun Bao","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023638404","display_name":"Zian Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zian Bao","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098770295","display_name":"Bie Binbin","orcid":"https://orcid.org/0009-0009-2639-7070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bie Binbin","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010690935","display_name":"Q. J. Duan","orcid":"https://orcid.org/0009-0009-3572-0933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"QingSong Duan","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, 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/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Fan","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences & University of Edinburgh, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences & University of Edinburgh, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113479631","display_name":"Hui Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Lei","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"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":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029865646","display_name":"Wei Lin","orcid":"https://orcid.org/0009-0009-7412-0113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031241828","display_name":"Min Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Xie","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Sciences, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014249013","display_name":"Xin Zhang","orcid":"https://orcid.org/0009-0006-0922-6649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, 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":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005955036","display_name":"Shuping Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuping Zhou","raw_affiliation_strings":["Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Grandhoo Inc. & Shenzhen Institute of Computing Science, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":19,"corresponding_author_ids":["https://openalex.org/A5102918743"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07751145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"106","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9891999959945679,"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/embedding","display_name":"Embedding","score":0.5850214958190918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5417365431785583},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.34968042373657227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2715279459953308}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5850214958190918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5417365431785583},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.34968042373657227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2715279459953308}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626246.3653372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1941880258","https://openalex.org/W1976732638","https://openalex.org/W1977041160","https://openalex.org/W1977379542","https://openalex.org/W1981590391","https://openalex.org/W2008271340","https://openalex.org/W2038412523","https://openalex.org/W2044022210","https://openalex.org/W2059554611","https://openalex.org/W2073471108","https://openalex.org/W2077518845","https://openalex.org/W2114887670","https://openalex.org/W2119320829","https://openalex.org/W2122789628","https://openalex.org/W2133409729","https://openalex.org/W2161163216","https://openalex.org/W2164625277","https://openalex.org/W2167333415","https://openalex.org/W2168506522","https://openalex.org/W2169940602","https://openalex.org/W2171332293","https://openalex.org/W2542998387","https://openalex.org/W2569536984","https://openalex.org/W2591700809","https://openalex.org/W2767681556","https://openalex.org/W2794573079","https://openalex.org/W2798649495","https://openalex.org/W2875652255","https://openalex.org/W2915915402","https://openalex.org/W2929941791","https://openalex.org/W2942740455","https://openalex.org/W2946504770","https://openalex.org/W2957204582","https://openalex.org/W2964961855","https://openalex.org/W2970727055","https://openalex.org/W2997574889","https://openalex.org/W2997756720","https://openalex.org/W3011807731","https://openalex.org/W3014705052","https://openalex.org/W3029269967","https://openalex.org/W3030481596","https://openalex.org/W3031504748","https://openalex.org/W3043376663","https://openalex.org/W3082197983","https://openalex.org/W3086284023","https://openalex.org/W3105977086","https://openalex.org/W3123375411","https://openalex.org/W3164439293","https://openalex.org/W3174036215","https://openalex.org/W3196877232","https://openalex.org/W3197847098","https://openalex.org/W4206031975","https://openalex.org/W4281879035","https://openalex.org/W4282010430","https://openalex.org/W4307079201","https://openalex.org/W4312851456","https://openalex.org/W4380433154","https://openalex.org/W4381621947","https://openalex.org/W4386298264","https://openalex.org/W4390532727","https://openalex.org/W6752663707"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2324615561","https://openalex.org/W2086120259","https://openalex.org/W2390279801","https://openalex.org/W2245170124","https://openalex.org/W2076393078","https://openalex.org/W2358668433","https://openalex.org/W3186982001"],"abstract_inverted_index":{"We":[0,140,148],"introduce":[1],"Rock,":[2,155],"a":[3,11,30,161],"system":[4],"for":[5,108],"cleaning":[6],"relational":[7],"data.":[8,100],"Rock":[9,72,102],"implements":[10],"framework":[12],"that":[13,36,128],"unifies":[14],"machine":[15],"learning":[16],"(ML)":[17],"and":[18,59,81,93,106,123,137,144,152,156],"logic":[19],"deduction":[20,83],"by":[21,63],"embedding":[22],"ML":[23],"classifiers":[24],"in":[25,84],"rules":[26,110,136],"as":[27],"predicates.":[28],"In":[29],"unified":[31],"process,":[32,87],"it":[33],"identifies":[34],"tuples":[35],"refer":[37],"to":[38],"the":[39,47,50,53,57,85,95,99,117,125,129,135,142,150],"same":[40,86],"real-world":[41],"entity,":[42],"catches":[43],"semantic":[44],"inconsistencies":[45],"among":[46],"entities,":[48,58],"deduces":[49],"timeliness":[51,82],"of":[52,56,90,98,134,146,154,163],"attribute":[54],"values":[55,62],"imputes":[60],"missing":[61],"possibly":[64],"extracting":[65],"data":[66],"from":[67,111,160],"knowledge":[68],"graphs.":[69],"That":[70],"is,":[71],"conducts":[73],"entity":[74],"resolution,":[75,77],"conflict":[76],"incomplete":[78],"information":[79],"imputation":[80],"makes":[88],"use":[89],"their":[91],"interactions":[92],"improves":[94],"overall":[96],"quality":[97],"Moreover,":[101],"supports":[103],"methods,":[104],"batch":[105],"incremental,":[107],"discovering":[109],"real-life":[112,164],"data,":[113],"detecting":[114],"errors":[115],"with":[116],"learned":[118,159],"rules,":[119],"accumulating":[120],"ground":[121,138],"truth,":[122],"fixing":[124],"errors,":[126],"such":[127],"corrections":[130],"are":[131],"logical":[132],"consequences":[133],"truth.":[139],"present":[141],"design":[143],"implementation":[145],"Rock.":[147],"evaluate":[149],"scalability":[151],"accuracy":[153],"share":[157],"lessons":[158],"variety":[162],"applications.":[165]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}