{"id":"https://openalex.org/W2988346468","doi":"https://doi.org/10.1109/cluster.2019.8891000","title":"Large-Scale Analysis of the Docker Hub Dataset","display_name":"Large-Scale Analysis of the Docker Hub Dataset","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2988346468","doi":"https://doi.org/10.1109/cluster.2019.8891000","mag":"2988346468"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2019.8891000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8891000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5000655733","display_name":"Nannan Zhao","orcid":"https://orcid.org/0000-0002-7897-5612"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nannan Zhao","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045054131","display_name":"Vasily Tarasov","orcid":"https://orcid.org/0000-0003-1424-9977"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasily Tarasov","raw_affiliation_strings":["IBM Research\u2014Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research\u2014Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083817094","display_name":"Hadeel Albahar","orcid":"https://orcid.org/0000-0002-4732-2707"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadeel Albahar","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054645319","display_name":"Ali Anwar","orcid":"https://orcid.org/0000-0003-4487-2436"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Anwar","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049824486","display_name":"Lukas Rupprecht","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lukas Rupprecht","raw_affiliation_strings":["IBM Research\u2014Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research\u2014Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109391071","display_name":"Dimitrios Skourtis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitrios Skourtis","raw_affiliation_strings":["IBM Research\u2014Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research\u2014Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619733","display_name":"Amit Warke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit S. Warke","raw_affiliation_strings":["IBM Research\u2014Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research\u2014Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342567","display_name":"Mohamed Mohamed","orcid":"https://orcid.org/0000-0002-3467-4252"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohamed Mohamed","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013454209","display_name":"Ali R. Butt","orcid":"https://orcid.org/0000-0002-0871-7263"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali R. Butt","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5000655733"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":5.9887,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96480343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9902999997138977,"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/data-deduplication","display_name":"Data deduplication","score":0.8454208374023438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7685961723327637},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.599489688873291},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5268743634223938},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5224406123161316},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4320236146450043}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8454208374023438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685961723327637},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.599489688873291},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5268743634223938},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5224406123161316},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4320236146450043},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2019.8891000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8891000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1829813581","https://openalex.org/W2006816934","https://openalex.org/W2050621158","https://openalex.org/W2075174112","https://openalex.org/W2131726714","https://openalex.org/W2136290019","https://openalex.org/W2140953464","https://openalex.org/W2294747777","https://openalex.org/W2572817543","https://openalex.org/W2598200822","https://openalex.org/W2605856244","https://openalex.org/W2612808279","https://openalex.org/W2763958491","https://openalex.org/W2789553548","https://openalex.org/W2962914897","https://openalex.org/W2970658103","https://openalex.org/W2970924126","https://openalex.org/W4243947286","https://openalex.org/W6697377647","https://openalex.org/W6748908680","https://openalex.org/W6766207752"],"related_works":["https://openalex.org/W2766145069","https://openalex.org/W3003602898","https://openalex.org/W2515214618","https://openalex.org/W2547510008","https://openalex.org/W2313358680","https://openalex.org/W2736204053","https://openalex.org/W2805733941","https://openalex.org/W2802582576","https://openalex.org/W3003962028","https://openalex.org/W2028024605"],"abstract_inverted_index":{"Docker":[0,41,47,54,78,94,111],"containers":[1,107],"have":[2],"become":[3],"a":[4,40,56,64,131],"prominent":[5],"solution":[6],"for":[7,52,106,138,157],"supporting":[8],"modern":[9],"enterprise":[10],"applications":[11],"due":[12],"to":[13,99,134],"the":[14,26,88,120,139,148],"highly":[15],"desirable":[16],"features":[17],"of":[18,25,45,76,90,119,150],"isolation,":[19],"low":[20],"overhead,":[21],"and":[22,86,110,145,154],"efficient":[23],"packaging":[24],"execution":[27],"environment.":[28],"Containers":[29],"are":[30,35,124],"created":[31],"from":[32],"images":[33,123],"which":[34,126],"shared":[36],"between":[37],"users":[38],"via":[39],"registry.":[42,140],"The":[43],"amount":[44],"data":[46,151],"registries":[48,112],"store":[49],"is":[50],"massive;":[51],"example,":[53,116],"Hub,":[55],"popular":[57],"public":[58,66],"registry,":[59],"stores":[60],"at":[61],"least":[62],"half":[63],"million":[65],"images.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"analyze":[72],"over":[73],"167":[74],"TB":[75],"uncompressed":[77],"Hub":[79],"images,":[80],"characterize":[81],"them":[82],"using":[83],"multiple":[84],"metrics":[85],"evaluate":[87],"potential":[89,133],"file-level":[91,128],"deduplication":[92,129],"in":[93,108,113,122],"Hub.":[95],"Our":[96,141],"analysis":[97],"helps":[98],"make":[100],"conscious":[101],"decisions":[102],"when":[103],"designing":[104],"storage":[105,136],"general":[109],"particular.":[114],"For":[115],"only":[117],"3%":[118],"files":[121],"unique,":[125],"means":[127],"has":[130],"great":[132],"save":[135],"space":[137],"findings":[142],"can":[143],"motivate":[144],"help":[146],"improve":[147],"design":[149],"reduction,":[152],"caching,":[153],"pulling":[155],"optimizations":[156],"registries.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
