{"id":"https://openalex.org/W2984976594","doi":"https://doi.org/10.1145/3366623.3368140","title":"Serverless Workflows for Indexing Large Scientific Data","display_name":"Serverless Workflows for Indexing Large Scientific Data","publication_year":2019,"publication_date":"2019-11-18","ids":{"openalex":"https://openalex.org/W2984976594","doi":"https://doi.org/10.1145/3366623.3368140","mag":"2984976594"},"language":"en","primary_location":{"id":"doi:10.1145/3366623.3368140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366623.3368140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Serverless Computing","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/A5079278437","display_name":"Tyler J. Skluzacek","orcid":"https://orcid.org/0000-0003-2242-4931"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler J. Skluzacek","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088145676","display_name":"Ryan Chard","orcid":"https://orcid.org/0000-0002-6781-7432"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Chard","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048915944","display_name":"Ryan Wong","orcid":"https://orcid.org/0000-0003-1066-7725"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Wong","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087300252","display_name":"Zhuozhao Li","orcid":"https://orcid.org/0000-0003-1903-6428"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuozhao Li","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001788942","display_name":"Yadu Babuji","orcid":"https://orcid.org/0000-0002-9162-6003"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yadu N. Babuji","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021403239","display_name":"Logan Ward","orcid":"https://orcid.org/0000-0002-1323-5939"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Logan Ward","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033890428","display_name":"Ben Blaiszik","orcid":"https://orcid.org/0000-0002-5326-4902"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Blaiszik","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne &amp; University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne &amp; University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5079278437"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":4.864,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96260708,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962000250816345,"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":0.9961000084877014,"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/metadata","display_name":"Metadata","score":0.9186709523200989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8249125480651855},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.7328217625617981},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7281827330589294},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.6792235374450684},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.5706773996353149},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.569740891456604},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.477670282125473},{"id":"https://openalex.org/keywords/data-mapping","display_name":"Data mapping","score":0.46175146102905273},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.4570602774620056},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45699188113212585},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.4567517042160034},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41366705298423767},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37363967299461365},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3532116115093231}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9186709523200989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249125480651855},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.7328217625617981},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7281827330589294},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.6792235374450684},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.5706773996353149},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.569740891456604},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.477670282125473},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.46175146102905273},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.4570602774620056},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45699188113212585},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.4567517042160034},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41366705298423767},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37363967299461365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3532116115093231}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366623.3368140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366623.3368140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Serverless Computing","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":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1136076469","https://openalex.org/W1980397870","https://openalex.org/W2001818158","https://openalex.org/W2108370395","https://openalex.org/W2116868464","https://openalex.org/W2186090720","https://openalex.org/W2206826311","https://openalex.org/W2467249088","https://openalex.org/W2546629842","https://openalex.org/W2565740142","https://openalex.org/W2592114463","https://openalex.org/W2789373058","https://openalex.org/W2854621940","https://openalex.org/W2906830849","https://openalex.org/W2906841437","https://openalex.org/W2917576038","https://openalex.org/W2940974134","https://openalex.org/W2943761765","https://openalex.org/W2967622523","https://openalex.org/W2990256517","https://openalex.org/W3015860937","https://openalex.org/W3104388511","https://openalex.org/W3121991495"],"related_works":["https://openalex.org/W3084772717","https://openalex.org/W3199469221","https://openalex.org/W2353291710","https://openalex.org/W2981561176","https://openalex.org/W2362378919","https://openalex.org/W2545809202","https://openalex.org/W1987988355","https://openalex.org/W4245065899","https://openalex.org/W2149827342","https://openalex.org/W202512329"],"abstract_inverted_index":{"The":[0],"use":[1,94],"and":[2,23,51,54,71,92,99,118,177],"reuse":[3],"of":[4,63,111,115,143,175],"scientific":[5,65,90,116,188],"data":[6,17,32,48,59,150,165,189],"is":[7],"ultimately":[8],"dependent":[9],"on":[10,128],"the":[11,38,73,141,164,168],"ability":[12],"to":[13,41,46,57,76,79,86,93,134,157,163],"understand":[14],"what":[15],"those":[16],"represent,":[18],"how":[19,24],"they":[20,25],"were":[21],"captured,":[22],"can":[26,154,181],"be":[27,77,155],"used.":[28],"In":[29],"many":[30],"ways,":[31],"are":[33,84],"only":[34],"as":[35,37,130],"useful":[36,78],"metadata":[39,74,88,96,121,137,183],"available":[40],"describe":[42,103],"them.":[43],"Unfortunately,":[44],"due":[45],"growing":[47],"volumes,":[49],"large":[50],"distributed":[52],"collaborations,":[53],"a":[55,108,131,172,185],"desire":[56],"store":[58],"for":[60,97],"long":[61],"periods":[62],"time,":[64],"\"data":[66],"lakes\"":[67],"quickly":[68],"become":[69],"disorganized":[70],"lack":[72],"necessary":[75],"researchers.":[80],"New":[81],"automated":[82],"approaches":[83],"needed":[85],"derive":[87,182],"from":[89,122,184],"files":[91,117],"these":[95],"organization":[98],"discovery.":[100],"Here":[101],"we":[102],"one":[104],"such":[105],"system,":[106],"Xtract,":[107],"service":[109,132],"capable":[110],"processing":[112],"vast":[113],"collections":[114],"automatically":[119],"extracting":[120],"diverse":[123],"file":[124],"types.":[125],"Xtract":[126,153,176],"relies":[127],"function":[129],"models":[133],"enable":[135],"scalable":[136],"extraction":[138],"by":[139],"orchestrating":[140],"execution":[142],"many,":[144],"short-running":[145],"extractor":[146],"functions.":[147],"To":[148],"reduce":[149],"transfer":[151],"costs,":[152],"configured":[156],"deploy":[158],"extractors":[159],"centrally":[160],"or":[161],"near":[162],"(i.e.,":[166],"at":[167],"edge).":[169],"We":[170],"present":[171],"prototype":[173],"implementation":[174],"demonstrate":[178],"that":[179],"it":[180],"7":[186],"TB":[187],"repository.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
