{"id":"https://openalex.org/W1056615582","doi":"https://doi.org/10.1145/2740908.2741695","title":"Scaling Down Distributed Infrastructure on Wimpy Machines for Personal Web Archiving","display_name":"Scaling Down Distributed Infrastructure on Wimpy Machines for Personal Web Archiving","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1056615582","doi":"https://doi.org/10.1145/2740908.2741695","mag":"1056615582"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2741695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","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/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082997975"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":4.0149,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94194461,"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":"1351","last_page":"1355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","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/T12607","display_name":"Personal Information Management and User Behavior","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/T11478","display_name":"Caching and Content Delivery","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"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7810481190681458},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5669635534286499},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.49765899777412415},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4872340261936188},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.44993898272514343},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4105042517185211},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.31938937306404114},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30134642124176025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810481190681458},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5669635534286499},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.49765899777412415},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4872340261936188},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.44993898272514343},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4105042517185211},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31938937306404114},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30134642124176025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2741695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","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":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W90672828","https://openalex.org/W153213769","https://openalex.org/W192446467","https://openalex.org/W1972305796","https://openalex.org/W2042486495","https://openalex.org/W2060269880","https://openalex.org/W2065132166","https://openalex.org/W2097411811","https://openalex.org/W2097510009","https://openalex.org/W2108566279","https://openalex.org/W2125200404","https://openalex.org/W2125421778","https://openalex.org/W2133394135","https://openalex.org/W2400669547","https://openalex.org/W2624304035"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4244478748","https://openalex.org/W2910064364","https://openalex.org/W4200136508"],"abstract_inverted_index":{"Warcbase":[0,36],"is":[1,78],"an":[2,31,41,56],"open-source":[3],"platform":[4],"for":[5,21,25,66],"storing,":[6],"managing,":[7],"and":[8,23,125],"analyzing":[9],"web":[10,68,85],"archives":[11],"using":[12],"modern":[13],"\"big":[14],"data\"":[15],"infrastructure":[16],"on":[17],"commodity":[18],"clusters---specifically,":[19],"HBase":[20],"storage":[22],"Hadoop":[24],"data":[26,122],"analytics.":[27],"This":[28],"paper":[29],"describes":[30],"effort":[32],"to":[33,80,108],"scale":[34],"\"down\"":[35],"onto":[37],"a":[38,49,61,72,83,95],"Raspberry":[39],"Pi,":[40],"inexpensive":[42],"single-board":[43],"computer":[44],"about":[45],"the":[46,89,92,100,106],"size":[47],"of":[48,51,91,102],"deck":[50],"playing":[52],"cards.":[53],"Apart":[54],"from":[55],"interesting":[57],"technology":[58],"demonstration,":[59],"such":[60,137],"design":[62],"presents":[63],"new":[64],"opportunities":[65],"personal":[67],"archiving,":[69],"in":[70],"enabling":[71],"low-cost,":[73],"low-power,":[74],"portable":[75],"device":[76],"that":[77,94,117,121,136],"able":[79],"continuously":[81],"capture":[82],"user's":[84],"browsing":[86,127],"history---not":[87],"only":[88],"URLs":[90],"pages":[93],"user":[96,107],"has":[97],"visited,":[98],"but":[99],"contents":[101],"those":[103],"pages---and":[104],"allowing":[105],"revisit":[109],"any":[110],"previously-encountered":[111],"page,":[112],"as":[113],"it":[114],"appeared":[115],"at":[116],"time.":[118],"Experiments":[119],"show":[120],"ingestion":[123],"throughput":[124],"temporal":[126],"latency":[128],"are":[129,139],"adequate":[130],"with":[131],"existing":[132],"hardware,":[133],"which":[134],"means":[135],"capabilities":[138],"already":[140],"feasible":[141],"today.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
