{"id":"https://openalex.org/W2613536717","doi":"https://doi.org/10.1145/3035918.3058740","title":"A Demo of the Data Civilizer System","display_name":"A Demo of the Data Civilizer System","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2613536717","doi":"https://doi.org/10.1145/3035918.3058740","mag":"2613536717"},"language":"en","primary_location":{"id":"doi:10.1145/3035918.3058740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3058740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/121460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raul Castro Fernandez","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042458153","display_name":"Essam Mansour","orcid":"https://orcid.org/0000-0002-1319-3484"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Essam Mansour","raw_affiliation_strings":["HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034660308","display_name":"Abdulhakim A. Qahtan","orcid":"https://orcid.org/0000-0001-8254-1764"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Abdulhakim A. Qahtan","raw_affiliation_strings":["HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018442175","display_name":"Wenbo Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbo Tao","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009128577","display_name":"Ziawasch Abedjan","orcid":"https://orcid.org/0000-0002-2846-1373"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziawasch Abedjan","raw_affiliation_strings":["TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089912733","display_name":"Ahmed K. Elmagarmid","orcid":"https://orcid.org/0000-0002-0044-458X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Elmagarmid","raw_affiliation_strings":["HBKU, Doha, MA, USA"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000141065","display_name":"Ihab F. Ilyas","orcid":"https://orcid.org/0000-0001-9052-9714"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5003690515"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.5802,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94557758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1639","last_page":"1642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9969000220298767,"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":0.9962999820709229,"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":0.7871366739273071},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7177203297615051},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.6083405017852783},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5374525189399719},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5357196927070618},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5257509350776672},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.48643040657043457},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.47242701053619385},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4630432724952698},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.459719181060791},{"id":"https://openalex.org/keywords/master-data","display_name":"Master data","score":0.4397548735141754},{"id":"https://openalex.org/keywords/task-management","display_name":"Task management","score":0.41311225295066833},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3425687551498413},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.336473286151886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29615941643714905},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09877422451972961},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09518969058990479},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.08773314952850342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07504984736442566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871366739273071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7177203297615051},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.6083405017852783},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5374525189399719},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5357196927070618},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5257509350776672},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.48643040657043457},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.47242701053619385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4630432724952698},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.459719181060791},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.4397548735141754},{"id":"https://openalex.org/C2780021488","wikidata":"https://www.wikidata.org/wiki/Q759682","display_name":"Task management","level":3,"score":0.41311225295066833},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3425687551498413},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.336473286151886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29615941643714905},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09877422451972961},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09518969058990479},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.08773314952850342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07504984736442566},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3035918.3058740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3058740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/121460","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/121460","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"website","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/121460","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/121460","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"website","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W2140116426","https://openalex.org/W2260616469","https://openalex.org/W2437030506","https://openalex.org/W2585438896","https://openalex.org/W6733170484"],"related_works":["https://openalex.org/W2949279097","https://openalex.org/W4216703","https://openalex.org/W2020045149","https://openalex.org/W1968076388","https://openalex.org/W4285502407","https://openalex.org/W3019007971","https://openalex.org/W2157176736","https://openalex.org/W2080078336","https://openalex.org/W4387639963","https://openalex.org/W2162883433"],"abstract_inverted_index":{"Finding":[0],"relevant":[1],"data":[2,10,30,34,43,58,79,100,110,116,118,122,126],"for":[3,115],"a":[4,17,83,128],"specific":[5],"task":[6,84],"from":[7,127],"the":[8,26,33,42,48,64,95,102],"numerous":[9],"sources":[11,31],"available":[12],"in":[13,98,135],"any":[14],"organization":[15],"is":[16,21,72,106],"daunting":[18],"task.":[19],"This":[20],"not":[22],"only":[23],"because":[24],"of":[25,28,35,69,80,131],"number":[27],"possible":[29],"where":[32],"interest":[36,81],"resides,":[37],"but":[38],"also":[39],"due":[40],"to":[41,82,89,93],"being":[44,51],"scattered":[45],"all":[46],"over":[47],"enterprise":[49],"and":[50,54,77,120,124],"typically":[52],"dirty":[53],"inconsistent.":[55],"In":[56],"practice,":[57],"scientists":[59],"are":[60],"routinely":[61],"reporting":[62],"that":[63],"majority":[65],"(more":[66],"than":[67],"80%)":[68],"their":[70],"effort":[71],"spent":[73],"finding,":[74],"cleaning,":[75,123],"integrating,":[76],"accessing":[78],"at":[85],"hand.":[86],"We":[87],"propose":[88],"demonstrate":[90],"DATA":[91,104],"CIVILIZER":[92,105],"ease":[94],"pain":[96],"faced":[97],"analyzing":[99],"\"in":[101],"wild\".":[103],"an":[107],"end-to-end":[108],"big":[109],"management":[111],"system":[112],"with":[113],"components":[114],"discovery,":[117],"integration":[119],"stitching,":[121],"querying":[125],"large":[129,136],"variety":[130],"storage":[132],"engines,":[133],"running":[134],"enterprises.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
