{"id":"https://openalex.org/W4386768520","doi":"https://doi.org/10.14778/3611540.3611628","title":"DataRinse: Semantic Transforms for Data Preparation Based on Code Mining","display_name":"DataRinse: Semantic Transforms for Data Preparation Based on Code Mining","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4386768520","doi":"https://doi.org/10.14778/3611540.3611628"},"language":"en","primary_location":{"id":"doi:10.14778/3611540.3611628","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611628","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/A5031546123","display_name":"Ibrahim Abdelaziz","orcid":"https://orcid.org/0000-0003-1449-5115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Abdelaziz","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012855077","display_name":"Julian Dolby","orcid":"https://orcid.org/0000-0002-6658-2678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Dolby","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013455098","display_name":"Udayan Khurana","orcid":"https://orcid.org/0000-0001-8113-1210"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Udayan Khurana","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035277014","display_name":"Horst Samulowitz","orcid":"https://orcid.org/0000-0002-6780-3217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horst Samulowitz","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kavitha Srinivas","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2222,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56943028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"16","issue":"12","first_page":"4090","last_page":"4093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"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":0.9977999925613403,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8164329528808594},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6937893033027649},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5455949902534485},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5329001545906067},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48730218410491943},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4818228781223297},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45208942890167236},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.4362197518348694},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35595065355300903},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31720978021621704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164329528808594},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6937893033027649},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5455949902534485},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5329001545906067},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48730218410491943},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4818228781223297},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45208942890167236},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4362197518348694},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35595065355300903},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31720978021621704},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3611540.3611628","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611628","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":7,"referenced_works":["https://openalex.org/W2612824201","https://openalex.org/W2884499287","https://openalex.org/W3021274480","https://openalex.org/W3208057978","https://openalex.org/W3215880744","https://openalex.org/W4206135750","https://openalex.org/W4256244129"],"related_works":["https://openalex.org/W2151320244","https://openalex.org/W1570829627","https://openalex.org/W2295023886","https://openalex.org/W4213243744","https://openalex.org/W2969365378","https://openalex.org/W2126667017","https://openalex.org/W2356864095","https://openalex.org/W2003932708","https://openalex.org/W2284877871","https://openalex.org/W3186878187"],"abstract_inverted_index":{"Data":[0],"preparation":[1,99],"is":[2,14,27,46,71,142],"a":[3,19,28,101,139,143],"crucial":[4],"first":[5],"step":[6],"to":[7,31,76,84,95,124,128,138,156],"any":[8,49],"data":[9,24,56,59,86,104],"analysis":[10,39,105,123],"problem.":[11],"This":[12],"task":[13],"largely":[15],"manual,":[16],"performed":[17],"by":[18,154],"person":[20],"familiar":[21],"with":[22,97],"the":[23,90,98,129,147],"domain.":[25],"DataRinse":[26,83,111,155],"system":[29,91,145],"designed":[30,94],"extract":[32],"relevant":[33,150],"transforms":[34,135],"from":[35],"large":[36,50],"scale":[37],"static":[38],"of":[40,42,100],"repositories":[41],"code.":[43],"Our":[44],"motivation":[45],"that":[47,69,89,110,133],"in":[48,118],"enterprise,":[51],"multiple":[52],"personas":[53],"such":[54,88,132],"as":[55],"engineers":[57],"and":[58,74],"scientists":[60],"work":[61],"on":[62,158],"similar":[63],"datasets.":[64],"However,":[65],"sharing":[66],"or":[67],"re-using":[68],"code":[70,93,119,151],"not":[72,113],"obvious":[73],"difficult":[75],"execute.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"demonstrate":[82],"handle":[85],"preparation,":[87],"recommends":[92],"help":[96],"column":[102],"for":[103],"more":[106],"generally.":[107],"We":[108],"show":[109],"does":[112],"simply":[114],"shard":[115],"expressions":[116,126],"observed":[117],"but":[120],"also":[121],"uses":[122],"group":[125],"applied":[127],"same":[130],"field":[131],"related":[134],"appear":[136],"coherently":[137],"user.":[140],"It":[141],"human-in-the-loop":[144],"where":[146],"users":[148],"select":[149],"snippets":[152],"produced":[153],"apply":[157],"their":[159],"dataset.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}