{"id":"https://openalex.org/W2798656727","doi":"https://doi.org/10.1145/3183713.3183760","title":"Meta-Dataflows","display_name":"Meta-Dataflows","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2798656727","doi":"https://doi.org/10.1145/3183713.3183760","mag":"2798656727"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3183760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-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/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/A5017128852","display_name":"William Culhane","orcid":"https://orcid.org/0000-0002-1427-9888"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William Culhane","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054074757","display_name":"Pijika Watcharapichat","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pijika Watcharapichat","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070529144","display_name":"Matthias Weidlich","orcid":"https://orcid.org/0000-0003-3325-7227"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Weidlich","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103803802","display_name":"Victoria Lopez Morales","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victoria Lopez Morales","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078842469","display_name":"Peter Pietzuch","orcid":"https://orcid.org/0000-0002-6963-5640"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Pietzuch","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003690515"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.4882,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92354838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1157","last_page":"1172"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9977999925613403,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9970999956130981,"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":0.9167840480804443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8495204448699951},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8214119672775269},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7057317495346069},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6258106827735901},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6037240028381348},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5801752805709839},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34764134883880615},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3399754762649536},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27706021070480347}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9167840480804443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8495204448699951},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8214119672775269},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7057317495346069},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6258106827735901},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6037240028381348},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5801752805709839},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34764134883880615},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3399754762649536},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27706021070480347},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183713.3183760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W60686164","https://openalex.org/W104184427","https://openalex.org/W255556494","https://openalex.org/W1480376833","https://openalex.org/W1480850417","https://openalex.org/W1487337216","https://openalex.org/W1493893823","https://openalex.org/W1985264830","https://openalex.org/W1988545508","https://openalex.org/W1994502095","https://openalex.org/W2002430341","https://openalex.org/W2006801410","https://openalex.org/W2011486414","https://openalex.org/W2027860831","https://openalex.org/W2037168816","https://openalex.org/W2038157364","https://openalex.org/W2046269252","https://openalex.org/W2078962046","https://openalex.org/W2086851811","https://openalex.org/W2097998348","https://openalex.org/W2100830825","https://openalex.org/W2105947650","https://openalex.org/W2118020555","https://openalex.org/W2121810937","https://openalex.org/W2125480047","https://openalex.org/W2131975293","https://openalex.org/W2152558130","https://openalex.org/W2157118109","https://openalex.org/W2170861540","https://openalex.org/W2171438172","https://openalex.org/W2183478929","https://openalex.org/W2266823300","https://openalex.org/W2293841640","https://openalex.org/W2547386789","https://openalex.org/W2617941540","https://openalex.org/W3118608800","https://openalex.org/W4235245586","https://openalex.org/W4298304654"],"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/W3083262785","https://openalex.org/W2799508461","https://openalex.org/W2150836909"],"abstract_inverted_index":{"Distributed":[0],"dataflow":[1,29],"systems":[2],"such":[3],"as":[4,28],"Apache":[5,8],"Spark":[6],"and":[7,85],"Flink":[9],"are":[10],"used":[11],"to":[12,67],"derive":[13],"new":[14],"insights":[15],"from":[16],"large":[17],"datasets.":[18],"While":[19],"they":[20,31,61],"efficiently":[21],"execute":[22],"concrete":[23],"data":[24,53],"processing":[25,47],"workflows,":[26,79],"expressed":[27],"graphs,":[30],"lack":[32],"generic":[33],"support":[34],"for":[35,77],"exploratory":[36,78],"workflows":[37],":":[38],"if":[39],"a":[40],"user":[41],"is":[42],"uncertain":[43],"about":[44],"the":[45,68],"correct":[46],"pipeline,":[48],"e.g.":[49],"in":[50,81],"terms":[51,82],"of":[52,58,83],"cleaning":[54],"strategy":[55],"or":[56],"choice":[57],"model":[59],"parameters,":[60],"must":[62],"repeatedly":[63],"submit":[64],"modified":[65],"jobs":[66],"system.":[69],"This,":[70],"however,":[71],"misses":[72],"out":[73],"on":[74],"optimisation":[75],"opportunities":[76],"both":[80],"scheduling":[84],"memory":[86],"allocation.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-05-07T00:00:00"}
