{"id":"https://openalex.org/W4408061150","doi":"https://doi.org/10.14778/3705829.3705832","title":"QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes","display_name":"QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes","publication_year":2024,"publication_date":"2024-10-01","ids":{"openalex":"https://openalex.org/W4408061150","doi":"https://doi.org/10.14778/3705829.3705832"},"language":"en","primary_location":{"id":"doi:10.14778/3705829.3705832","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3705829.3705832","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/A5112122466","display_name":"Tang Xiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiu Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021066656","display_name":"Wenhao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064646829","display_name":"Sai Wu","orcid":"https://orcid.org/0000-0002-1866-9197"},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sai Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056066639","display_name":"Chang Yao","orcid":"https://orcid.org/0000-0002-1187-6257"},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Yao","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014098250","display_name":"Gongsheng Yuan","orcid":"https://orcid.org/0000-0002-7992-3179"},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongsheng Yuan","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116465036","display_name":"Shanshan Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanshan Ying","raw_affiliation_strings":["ApeCloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ApeCloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100389286","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-7483-0045"},"institutions":[{"id":"https://openalex.org/I4210126530","display_name":"Data Assurance and Communication Security","ror":"https://ror.org/02z2gfm30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210126530","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute","institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5112122466"],"corresponding_institution_ids":["https://openalex.org/I4210126530","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.34,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84115742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"18","issue":"2","first_page":"108","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9965999722480774,"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":0.5915806293487549},{"id":"https://openalex.org/keywords/post-hoc","display_name":"Post hoc","score":0.4574747085571289},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08535963296890259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5915806293487549},{"id":"https://openalex.org/C2992886853","wikidata":"https://www.wikidata.org/wiki/Q18381816","display_name":"Post hoc","level":2,"score":0.4574747085571289},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08535963296890259},{"id":"https://openalex.org/C199343813","wikidata":"https://www.wikidata.org/wiki/Q12128","display_name":"Dentistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3705829.3705832","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3705829.3705832","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":30,"referenced_works":["https://openalex.org/W1570856340","https://openalex.org/W2078446440","https://openalex.org/W2112129552","https://openalex.org/W2123544675","https://openalex.org/W2424304400","https://openalex.org/W2427822648","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2950817225","https://openalex.org/W2953502323","https://openalex.org/W2970992672","https://openalex.org/W3031580546","https://openalex.org/W3034835156","https://openalex.org/W3098605233","https://openalex.org/W3108851861","https://openalex.org/W3160974509","https://openalex.org/W3174637548","https://openalex.org/W3180107114","https://openalex.org/W4221143046","https://openalex.org/W4225502177","https://openalex.org/W4281826654","https://openalex.org/W4283733706","https://openalex.org/W4285335450","https://openalex.org/W4311887664","https://openalex.org/W4312537169","https://openalex.org/W4321448337","https://openalex.org/W4375928372","https://openalex.org/W4384659457","https://openalex.org/W4386123414","https://openalex.org/W4389519829"],"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":{"Query":[0],"processing":[1,116],"over":[2],"data":[3,12,17,51,67,97,117],"lakes":[4],"is":[5],"a":[6,32,41,59,109,124],"challenging":[7],"task,":[8],"often":[9],"requiring":[10],"extensive":[11,141],"pre-processing":[13],"activities":[14],"such":[15],"as":[16],"cleaning,":[18],"transformation,":[19],"and":[20,160],"loading.":[21],"However,":[22],"the":[23,46,86,96],"advent":[24],"of":[25,111,115,157],"Large":[26],"Language":[27],"Models":[28],"(LLMs)":[29],"has":[30],"illuminated":[31],"new":[33],"pathway":[34],"to":[35,44,94],"address":[36],"these":[37],"complexities":[38],"by":[39,77],"offering":[40],"unified":[42],"approach":[43],"understanding":[45],"diverse":[47],"datasets":[48],"submerged":[49],"in":[50,155],"lakes.":[52,68],"In":[53],"this":[54],"paper,":[55],"we":[56,106],"introduce":[57],"QueryArtisan,":[58],"novel":[60],"LLM-powered":[61],"analytic":[62],"tool":[63],"specifically":[64],"designed":[65],"for":[66,81,88,136],"QueryArtisan":[69,122,150],"transcends":[70],"traditional":[71],"ETL":[72],"(Extract,":[73],"Transform,":[74],"Load)":[75],"processes":[76],"generating":[78],"just-intime":[79],"code":[80,133],"dataset-specific":[82],"queries.":[83],"It":[84],"eliminates":[85],"need":[87],"an":[89],"intermediary":[90],"schema,":[91],"enabling":[92],"users":[93],"query":[95,127,138],"lake":[98],"directly":[99],"using":[100],"natural":[101],"language.":[102],"To":[103],"achieve":[104],"this,":[105],"have":[107],"developed":[108],"suite":[110],"heterogeneous":[112],"operators":[113],"capable":[114],"across":[118],"various":[119],"modalities.":[120],"Additionally,":[121],"incorporates":[123],"cost":[125],"model-based":[126],"optimization":[128],"technique,":[129],"significantly":[130],"enhancing":[131],"its":[132],"generation":[134],"capabilities":[135],"efficient":[137],"resolution.":[139],"Our":[140],"experimental":[142],"evaluations,":[143],"conducted":[144],"with":[145],"real-life":[146],"datasets,":[147],"demonstrate":[148],"that":[149],"markedly":[151],"outperforms":[152],"existing":[153],"solutions":[154],"terms":[156],"effectiveness,":[158],"efficiency":[159],"usability.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}