{"id":"https://openalex.org/W4318186097","doi":"https://doi.org/10.1109/bigdata55660.2022.10020380","title":"Pseudonymization at Scale: OLCF\u2019s Summit Usage Data Case Study","display_name":"Pseudonymization at Scale: OLCF\u2019s Summit Usage Data Case Study","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318186097","doi":"https://doi.org/10.1109/bigdata55660.2022.10020380"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020380","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1928931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044863788","display_name":"Ketan Maheshwari","orcid":"https://orcid.org/0000-0003-3800-662X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ketan Maheshwari","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034261249","display_name":"Sean R. Wilkinson","orcid":"https://orcid.org/0000-0002-1443-7479"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean R. Wilkinson","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023589713","display_name":"Alex May","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex May","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079278437","display_name":"Tyler J. Skluzacek","orcid":"https://orcid.org/0000-0003-2242-4931"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Skluzacek","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111987089","display_name":"Olga Kuchar","orcid":"https://orcid.org/0009-0000-2475-4710"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga A. Kuchar","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072339196","display_name":"Rafael Ferreira da Silva","orcid":"https://orcid.org/0000-0002-1720-0928"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira da Silva","raw_affiliation_strings":["Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,NCCS/OLCF,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"NCCS/OLCF, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044863788"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74378585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3432","last_page":"3440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9979000091552734,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8405075073242188},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7736595869064331},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7479961514472961},{"id":"https://openalex.org/keywords/summit","display_name":"Summit","score":0.7070014476776123},{"id":"https://openalex.org/keywords/unix","display_name":"Unix","score":0.6047384142875671},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5000736713409424},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44544875621795654},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4353247284889221},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3815552890300751},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3113444447517395},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2963925004005432},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24463236331939697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12254124879837036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405075073242188},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7736595869064331},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7479961514472961},{"id":"https://openalex.org/C2778848561","wikidata":"https://www.wikidata.org/wiki/Q207326","display_name":"Summit","level":2,"score":0.7070014476776123},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.6047384142875671},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5000736713409424},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44544875621795654},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4353247284889221},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3815552890300751},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3113444447517395},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2963925004005432},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24463236331939697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12254124879837036},{"id":"https://openalex.org/C100970517","wikidata":"https://www.wikidata.org/wiki/Q52107","display_name":"Physical geography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020380","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1928931","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1928931","pdf_url":"https://www.osti.gov/servlets/purl/1928931","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1928931","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1928931","pdf_url":"https://www.osti.gov/servlets/purl/1928931","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318186097.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1971514365","https://openalex.org/W2090502325","https://openalex.org/W2147598193","https://openalex.org/W2158197021","https://openalex.org/W2302501749","https://openalex.org/W2418418119","https://openalex.org/W2564864435","https://openalex.org/W2583718094","https://openalex.org/W2902041647","https://openalex.org/W2972201948","https://openalex.org/W3159974995","https://openalex.org/W3203002808","https://openalex.org/W3206611000","https://openalex.org/W4205140476","https://openalex.org/W4223441700","https://openalex.org/W4229054296","https://openalex.org/W4281389060","https://openalex.org/W4285145645","https://openalex.org/W4311797354","https://openalex.org/W6731276349","https://openalex.org/W6777308083","https://openalex.org/W6810705264"],"related_works":["https://openalex.org/W1982074779","https://openalex.org/W4241376597","https://openalex.org/W3203904831","https://openalex.org/W630050097","https://openalex.org/W4246070377","https://openalex.org/W2280577319","https://openalex.org/W2352077919","https://openalex.org/W4246682738","https://openalex.org/W1538842854","https://openalex.org/W2905384139"],"abstract_inverted_index":{"The":[0,147],"analysis":[1],"of":[2,5,10,29,55,118,158,179,182,203,221,230,236,253,294],"vast":[3],"amounts":[4],"data":[6,33,76,88,113,145,184,190],"and":[7,26,32,50,131,140,167,218,264,303,307],"the":[8,53,56,108,128,156,180,183,189,197,201,204,207,219,234,250,254,273,299,305],"processing":[9],"complex":[11],"computational":[12,31],"jobs":[13],"have":[14],"traditionally":[15],"relied":[16],"upon":[17],"high":[18],"performance":[19],"computing":[20],"(HPC)":[21],"systems,":[22],"which":[23,160,172,199,224],"offer":[24],"reliable":[25],"efficient":[27],"management":[28],"large-scale":[30],"resources.":[34],"Understanding":[35],"these":[36],"analyses\u2019":[37],"needs":[38],"is":[39,62,80,211,225],"paramount":[40],"for":[41,64,138,188],"designing":[42],"solutions":[43],"that":[44,170,240,267],"can":[45],"lead":[46],"to":[47,74,81,91,142,165,185,195,206,271,287],"better":[48],"science,":[49],"similarly,":[51],"understanding":[52],"characteristics":[54,84],"user":[57,66,78,105],"behavior":[58,79,106,252],"on":[59,68,244,256,282],"those":[60],"systems":[61,261],"important":[63],"improving":[65],"experiences":[67],"HPC":[69,246,260],"systems.":[70],"A":[71],"common":[72],"approach":[73],"gathering":[75],"about":[77,107,155],"extract":[82],"workload":[83],"from":[85,114,277],"system":[86,92],"log":[87],"available":[89],"only":[90],"administrators.":[93],"Recently":[94],"at":[95,262],"Oak":[96],"Ridge":[97],"Leadership":[98],"Computing":[99],"Facility":[100],"(OLCF),":[101],"however,":[102],"we":[103,126,168,265,268,297],"unveiled":[104],"Summit":[109],"supercomputer":[110],"by":[111],"collecting":[112],"a":[115,237,283,292],"user\u2019s":[116],"point":[117],"view":[119],"with":[120],"ordinary":[121],"Unix":[122],"commands.In":[123],"this":[124,136,295],"paper,":[125],"discuss":[127],"process,":[129],"challenges,":[130],"lessons":[132],"learned":[133],"while":[134],"preparing":[135],"dataset":[137,149,205,302],"publication":[139],"submission":[141],"an":[143,278],"open":[144],"challenge.":[146,191],"original":[148],"contains":[150],"personal":[151],"identifiable":[152],"information":[153],"(PII)":[154],"users":[157],"OLCF":[159],"needed":[161],"be":[162,186,242],"masked":[163],"prior":[164],"publication,":[166],"determined":[169],"anonymization,":[171,217],"scrubs":[173],"PII":[174],"completely,":[175],"destroyed":[176],"too":[177],"much":[178],"structure":[181],"interesting":[187],"We":[192,248],"instead":[193],"chose":[194],"pseudonymize":[196],"dataset,":[198,223],"reduced":[200],"linkability":[202],"users\u2019":[208],"identities.":[209],"Pseudonymization":[210],"significantly":[212],"more":[213],"computationally":[214],"expensive":[215],"than":[216],"size":[220],"our":[222],"approximately":[226],"175":[227],"million":[228],"lines":[229],"raw":[231],"text,":[232],"necessitated":[233],"development":[235],"parallelized":[238],"workflow":[239,255],"could":[241],"reused":[243],"different":[245],"machines.":[247],"demonstrate":[249],"scaling":[251],"two":[257],"leadership":[258],"class":[259],"OLCF,":[263],"show":[266],"were":[269],"able":[270],"bring":[272],"overall":[274],"makespan":[275],"time":[276],"impractical":[279],"20+":[280],"hours":[281],"single":[284],"node":[285],"down":[286],"around":[288],"2":[289],"hours.":[290],"As":[291],"result":[293],"work,":[296],"release":[298],"entire":[300],"pseudonymized":[301],"make":[304],"workflows":[306],"source":[308],"code":[309],"publicly":[310],"available.":[311]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
