{"id":"https://openalex.org/W2142031898","doi":"https://doi.org/10.14778/1687553.1687568","title":"Building a high-level dataflow system on top of Map-Reduce","display_name":"Building a high-level dataflow system on top of Map-Reduce","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2142031898","doi":"https://doi.org/10.14778/1687553.1687568","mag":"2142031898"},"language":"en","primary_location":{"id":"doi:10.14778/1687553.1687568","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687553.1687568","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/A5049564657","display_name":"Alan Gates","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alan F. Gates","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038385666","display_name":"Olga Natkovich","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olga Natkovich","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069246862","display_name":"Shubham Chopra","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shubham Chopra","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001235213","display_name":"PRADEEP KAMATH","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pradeep Kamath","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013557732","display_name":"Shravan Narayanamurthy","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shravan M. Narayanamurthy","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109881550","display_name":"Christopher Olston","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher Olston","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019808162","display_name":"Benjamin Reed","orcid":"https://orcid.org/0000-0002-8620-0331"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Reed","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023679021","display_name":"Santhosh Srinivasan","orcid":"https://orcid.org/0000-0002-3869-7443"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Santhosh Srinivasan","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101897152","display_name":"Utkarsh Srivastava","orcid":"https://orcid.org/0009-0002-7952-559X"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Utkarsh Srivastava","raw_affiliation_strings":["Yahoo!, Inc","Yahoo! Inc.,#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Inc","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc.,#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5049564657"],"corresponding_institution_ids":["https://openalex.org/I1325784139"],"apc_list":null,"apc_paid":null,"fwci":34.3091,"has_fulltext":false,"cited_by_count":412,"citation_normalized_percentile":{"value":0.99858718,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"2","issue":"2","first_page":"1414","last_page":"1425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9991000294685364,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"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/dataflow","display_name":"Dataflow","score":0.9096580147743225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8459801077842712},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5658571124076843},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5414137840270996},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.49820899963378906},{"id":"https://openalex.org/keywords/map-reduce","display_name":"Map reduce","score":0.4318329095840454},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4116988182067871},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37843823432922363},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3269695043563843},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24701371788978577},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.1680126190185547}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9096580147743225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459801077842712},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5658571124076843},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5414137840270996},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.49820899963378906},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.4318329095840454},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4116988182067871},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37843823432922363},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3269695043563843},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24701371788978577},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.1680126190185547}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1687553.1687568","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687553.1687568","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1493893823","https://openalex.org/W1597532222","https://openalex.org/W1605782097","https://openalex.org/W1755889808","https://openalex.org/W1989078417","https://openalex.org/W2049455633","https://openalex.org/W2098935637","https://openalex.org/W2103201239","https://openalex.org/W2112491581","https://openalex.org/W2119400430","https://openalex.org/W2119714163","https://openalex.org/W2122465391","https://openalex.org/W2126354234","https://openalex.org/W2143377704","https://openalex.org/W6635650928","https://openalex.org/W6678120442"],"related_works":["https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4239447582","https://openalex.org/W2171015181","https://openalex.org/W4225271228","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640","https://openalex.org/W2048507547"],"abstract_inverted_index":{"Increasingly,":[0],"organizations":[1],"capture,":[2],"transform":[3],"and":[4,14,89,106,123,128,142,151,172,179],"analyze":[5],"enormous":[6],"data":[7,112],"sets.":[8],"Prominent":[9],"examples":[10],"include":[11],"internet":[12],"companies":[13],"e-science.":[15],"The":[16],"Map-Reduce":[17,52,140,147,181],"scalable":[18],"dataflow":[19,30,96,122],"paradigm":[20],"has":[21],"become":[22],"popular":[23],"for":[24],"these":[25],"applications.":[26],"Its":[27],"simple,":[28],"explicit":[29,121],"programming":[31],"model":[32],"is":[33,93],"favored":[34],"by":[35,79,157],"some":[36],"over":[37],"the":[38,45,48,61,145,158,165],"traditional":[39],"high-level":[40,95,111],"declarative":[41],"approach:":[42],"SQL.":[43],"On":[44],"other":[46],"hand,":[47],"extreme":[49],"simplicity":[50],"of":[51,139],"leads":[53],"to":[54,58],"much":[55],"low-level":[56],"hacking":[57],"deal":[59],"with":[60,125],"many-step,":[62],"branching":[63],"dataflows":[64],"that":[65,98],"arise":[66],"in":[67,119,144,169],"practice.":[68],"Moreover,":[69],"users":[70],"must":[71],"repeatedly":[72],"code":[73],"standard":[74],"operations":[75],"such":[76],"as":[77],"join":[78],"hand.":[80],"These":[81],"practices":[82],"waste":[83],"time,":[84],"introduce":[85],"bugs,":[86],"harm":[87],"readability,":[88],"impede":[90],"optimizations.":[91],"Pig":[92,108,133,150,177],"a":[94,101],"system":[97],"aims":[99],"at":[100],"sweet":[102],"spot":[103],"between":[104,176],"SQL":[105],"Map-Reduce.":[107],"offers":[109],"SQL-style":[110],"manipulation":[113],"constructs,":[114],"which":[115],"can":[116],"be":[117],"assembled":[118],"an":[120],"interleaved":[124],"custom":[126],"Map-":[127],"Reduce-style":[129],"functions":[130],"or":[131],"executables.":[132],"programs":[134],"are":[135,153],"compiled":[136],"into":[137],"sequences":[138],"jobs,":[141],"executed":[143],"Hadoop":[146,152],"environment.":[148],"Both":[149],"open-source":[154],"projects":[155],"administered":[156],"Apache":[159],"Software":[160],"Foundation.":[161],"This":[162],"paper":[163],"describes":[164],"challenges":[166],"we":[167],"faced":[168],"developing":[170],"Pig,":[171],"reports":[173],"performance":[174],"comparisons":[175],"execution":[178],"raw":[180],"execution.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":42},{"year":2014,"cited_by_count":62},{"year":2013,"cited_by_count":63},{"year":2012,"cited_by_count":43}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}
