{"id":"https://openalex.org/W2970228335","doi":"https://doi.org/10.14778/3352063.3352108","title":"Data Civilizer 2.0","display_name":"Data Civilizer 2.0","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2970228335","doi":"https://doi.org/10.14778/3352063.3352108","mag":"2970228335"},"language":"en","primary_location":{"id":"doi:10.14778/3352063.3352108","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352108","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/137529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004937696","display_name":"El Kindi Rezig","orcid":"https://orcid.org/0000-0002-5187-3499"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"El Kindi Rezig","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049926126","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0001-9909-8607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018442175","display_name":"Wenbo Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbo Tao","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["HBKU","MIT CSAIL Qatar Computing Research Institute, HBKU"],"affiliations":[{"raw_affiliation_string":"HBKU","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL Qatar Computing Research Institute, HBKU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HBKU","MIT CSAIL Qatar Computing Research Institute, HBKU"],"affiliations":[{"raw_affiliation_string":"HBKU","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL Qatar Computing Research Institute, HBKU","institution_ids":[]}]},{"author_position":"last","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 K. Elmagarmid","raw_affiliation_strings":["HBKU","MIT CSAIL Qatar Computing Research Institute, HBKU"],"affiliations":[{"raw_affiliation_string":"HBKU","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL Qatar Computing Research Institute, HBKU","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5004937696"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6032,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97159972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"12","first_page":"1954","last_page":"1957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"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/T11937","display_name":"Research Data Management Practices","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/debugger","display_name":"Debugger","score":0.9039567708969116},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8670969009399414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808346748352051},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7164755463600159},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49261313676834106},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4907589852809906},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.44444891810417175},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4404309391975403},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.4398091435432434},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4210509955883026},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4095477759838104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39071330428123474},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.379913866519928},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36556220054626465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438921570777893},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3204513192176819},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27879244089126587}],"concepts":[{"id":"https://openalex.org/C2778485113","wikidata":"https://www.wikidata.org/wiki/Q193231","display_name":"Debugger","level":3,"score":0.9039567708969116},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8670969009399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808346748352051},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7164755463600159},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49261313676834106},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4907589852809906},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.44444891810417175},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4404309391975403},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.4398091435432434},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4210509955883026},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4095477759838104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39071330428123474},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.379913866519928},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36556220054626465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438921570777893},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3204513192176819},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27879244089126587}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/3352063.3352108","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352108","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"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137529","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137529","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB Endowment","raw_type":"Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137529.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137529.2","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB Endowment","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:iris.unimore.it:11380/1191053","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1191053","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/137529","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137529","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB Endowment","raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2384569204","https://openalex.org/W2432911982","https://openalex.org/W2466758040","https://openalex.org/W2542998387","https://openalex.org/W2547386789","https://openalex.org/W2585438896","https://openalex.org/W2591700809","https://openalex.org/W2613536717","https://openalex.org/W2885678825","https://openalex.org/W2889353337","https://openalex.org/W2898269683","https://openalex.org/W2951376138","https://openalex.org/W3104024780","https://openalex.org/W4313371817","https://openalex.org/W6733170484"],"related_works":["https://openalex.org/W2800641345","https://openalex.org/W2886673879","https://openalex.org/W564953056","https://openalex.org/W2061184006","https://openalex.org/W2381239448","https://openalex.org/W4236910510","https://openalex.org/W2092932442","https://openalex.org/W2543963479","https://openalex.org/W1751798423","https://openalex.org/W2583000271"],"abstract_inverted_index":{"Data":[0,53,73,107],"scientists":[1,112],"spend":[2],"over":[3],"80%":[4],"of":[5,52,65],"their":[6,119,126],"time":[7],"(1)":[8],"parameter-tuning":[9],"machine":[10,20,46,122],"learning":[11,21,47,123],"models":[12],"and":[13,19,45,60,93,121],"(2)":[14],"iterating":[15],"between":[16],"data":[17,43,58,91],"cleaning":[18,44,59,120],"model":[22],"execution.":[23],"While":[24],"there":[25,34],"are":[26],"existing":[27],"efforts":[28],"to":[29,110],"support":[30],"the":[31,114],"first":[32],"requirement,":[33],"is":[35],"currently":[36],"no":[37],"integrated":[38],"workflow":[39,78,95],"system":[40,79,86],"that":[41],"couples":[42],"development.":[48],"The":[49],"previous":[50],"version":[51],"Civilizer":[54,74,108],"was":[55],"geared":[56],"towards":[57],"discovery":[61],"using":[62],"a":[63,89,94],"set":[64],"pre-defined":[66],"tools.":[67],"In":[68,83,98],"this":[69,85,99],"paper,":[70],"we":[71,101,105],"introduce":[72],"2.0,":[75],"an":[76],"end-to-end":[77],"satisfying":[80],"both":[81],"requirements.":[82],"addition,":[84],"also":[87],"supports":[88],"sophisticated":[90],"debugger":[92],"visualization":[96],"system.":[97],"demo,":[100],"will":[102],"show":[103],"how":[104],"used":[106],"2.0":[109],"help":[111],"at":[113],"Massachusetts":[115],"General":[116],"Hospital":[117],"build":[118],"pipeline":[124],"on":[125],"30TB":[127],"brain":[128],"activity":[129],"dataset.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-09-05T00:00:00"}
