{"id":"https://openalex.org/W2022280610","doi":"https://doi.org/10.1145/2110497.2110501","title":"Provenance for MapReduce-based data-intensive workflows","display_name":"Provenance for MapReduce-based data-intensive workflows","publication_year":2011,"publication_date":"2011-11-14","ids":{"openalex":"https://openalex.org/W2022280610","doi":"https://doi.org/10.1145/2110497.2110501","mag":"2022280610"},"language":"en","primary_location":{"id":"doi:10.1145/2110497.2110501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2110497.2110501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th workshop on Workflows in support of large-scale science","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mdsoar.org/bitstreams/f387d40b-1b79-4f9a-bd49-c7ac751f3aff/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002534857","display_name":"Daniel Crawl","orcid":"https://orcid.org/0000-0003-1013-8241"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Crawl","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101750217","display_name":"Jianwu Wang","orcid":"https://orcid.org/0000-0002-9933-1170"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianwu Wang","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028701796","display_name":"\u0130lkay Alt\u0131nta\u015f","orcid":"https://orcid.org/0000-0002-2196-0305"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilkay Altintas","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11937","display_name":"Research Data Management Practices","score":0.9955999851226807,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9933000206947327,"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/workflow","display_name":"Workflow","score":0.7740742564201355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530073523521423},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.6825574040412903},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3333701193332672},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05555948615074158}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7740742564201355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530073523521423},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.6825574040412903},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3333701193332672},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05555948615074158},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2110497.2110501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2110497.2110501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th workshop on Workflows in support of large-scale science","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/31655","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/31655","pdf_url":"https://mdsoar.org/bitstreams/f387d40b-1b79-4f9a-bd49-c7ac751f3aff/download","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/m2anpc-c4tr","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2anpc-c4tr","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:mdsoar.org:11603/31655","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/31655","pdf_url":"https://mdsoar.org/bitstreams/f387d40b-1b79-4f9a-bd49-c7ac751f3aff/download","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2022280610.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W50182133","https://openalex.org/W126044612","https://openalex.org/W135267584","https://openalex.org/W1493893823","https://openalex.org/W1501507312","https://openalex.org/W1510543252","https://openalex.org/W1578415644","https://openalex.org/W1582664144","https://openalex.org/W1780933788","https://openalex.org/W1976860187","https://openalex.org/W1982107955","https://openalex.org/W1983833794","https://openalex.org/W2037712729","https://openalex.org/W2055043387","https://openalex.org/W2090950090","https://openalex.org/W2120676687","https://openalex.org/W2120678638","https://openalex.org/W2128226234","https://openalex.org/W2129603526","https://openalex.org/W2133964524","https://openalex.org/W2168281637","https://openalex.org/W2169411125","https://openalex.org/W2171815523","https://openalex.org/W2173213060","https://openalex.org/W4246367117"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613"],"abstract_inverted_index":{"MapReduce":[0,29,45,84,92,115],"has":[1],"been":[2,68],"widely":[3],"adopted":[4],"by":[5],"many":[6],"business":[7],"and":[8,23,32,59,154,163],"scientific":[9],"applications":[10],"for":[11,21,44,122],"data-intensive":[12],"processing":[13],"of":[14,56,91,158,161],"large":[15],"datasets.":[16],"There":[17],"are":[18],"increasing":[19],"efforts":[20],"workflows":[22,58,93],"systems":[24],"to":[25,53,79,87,110,131,135,149],"work":[26,38,82],"with":[27,171],"the":[28,33,47,89,96,120,123,132,151,159],"programming":[30,42,147],"model":[31,43,106,141],"Hadoop":[34],"environment":[35],"including":[36],"our":[37,80],"on":[39,62,83,142],"a":[40,104,114,146],"higher-level":[41],"within":[46],"Kepler":[48,86],"Scientific":[49],"Workflow":[50],"System.":[51],"However,":[52],"date,":[54],"provenance":[55,90,112,121,137,166],"MapReduce-based":[57],"its":[60],"effects":[61],"workflow":[63,124],"execution":[64],"performance":[65],"have":[66],"not":[67],"studied":[69],"in":[70,85],"depth.":[71],"In":[72,99],"this":[73,139,165],"paper,":[74],"we":[75,101],"present":[76],"an":[77,129,156],"extension":[78,130],"earlier":[81],"record":[88,136],"created":[94],"using":[95,138,168],"Kepler+Hadoop":[97,133],"framework.":[98],"particular,":[100],"present:":[102],"(i)":[103],"data":[105,140],"that":[107,125],"is":[108],"able":[109],"capture":[111],"inside":[113],"job":[116],"as":[117,119],"well":[118],"submitted":[126],"it;":[127],"(ii)":[128],"architecture":[134],"MySQL":[143],"Cluster;":[144],"(iii)":[145],"interface":[148],"query":[150],"collected":[152],"information;":[153],"(iv)":[155],"evaluation":[157],"scalability":[160],"collecting":[162],"querying":[164],"information":[167],"two":[169],"scenarios":[170],"different":[172],"characteristics.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}