{"id":"https://openalex.org/W2137133993","doi":"https://doi.org/10.1145/974750.974752","title":"Archiving scientific data","display_name":"Archiving scientific data","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2137133993","doi":"https://doi.org/10.1145/974750.974752","mag":"2137133993"},"language":"en","primary_location":{"id":"doi:10.1145/974750.974752","doi":"https://doi.org/10.1145/974750.974752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/974750.974752","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-100","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/a2db6f32-4981-42e7-bc38-c4766b17ae0c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087078518","display_name":"Peter Buneman","orcid":"https://orcid.org/0009-0004-9056-8587","observed_orcids":["https://orcid.org/0009-0004-9056-8587"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Buneman","raw_affiliation_strings":["University of Edinburgh, Edinburgh, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039619350","display_name":"Sanjeev Khanna","orcid":"https://orcid.org/0009-0000-2601-1689","observed_orcids":["https://orcid.org/0009-0000-2601-1689"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khanna","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, PA","University of Pennsylvania, Philadelphia, Pennsylvania, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, PA#TAB#","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103793743","display_name":"Keishi Tajima","orcid":"https://orcid.org/0000-0001-8226-3442","observed_orcids":["https://orcid.org/0000-0001-8226-3442"]},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keishi Tajima","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007789","display_name":"Wang-Chiew Tan","orcid":"https://orcid.org/0009-0008-4174-7545","observed_orcids":["https://orcid.org/0009-0008-4174-7545"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Chiew Tan","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, California","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.5922,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99205323,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"29","issue":"1","first_page":"2","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.8823000192642212,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.8823000192642212,"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/T11269","display_name":"Algorithms and Data Compression","score":0.06759999692440033,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.011099999770522118,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scientific-data-archiving","display_name":"scientific data archiving","score":0.9599999785423279},{"id":"https://openalex.org/keywords/database-versioning","display_name":"database versioning","score":0.7960000038146973},{"id":"https://openalex.org/keywords/hierarchical-data","display_name":"hierarchical data","score":0.8989999890327454},{"id":"https://openalex.org/keywords/semantic-continuity","display_name":"semantic continuity","score":0.5139999985694885},{"id":"https://openalex.org/keywords/temporal-queries","display_name":"temporal queries","score":0.593999981880188},{"id":"https://openalex.org/keywords/xml-compression","display_name":"XML compression","score":0.8500000238418579},{"id":"https://openalex.org/keywords/spatial-efficiency","display_name":"space efficiency","score":0.6729999780654907},{"id":"https://openalex.org/keywords/index-structures","display_name":"index structures","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837942481040955},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5966899991035461},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.5747773051261902},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5411720275878906},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4374249577522278},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.434938907623291},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42664092779159546},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4181953966617584},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.41585347056388855},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3562237620353699},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34923726320266724},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19507437944412231},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19145607948303223},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/974750.974752","doi":"https://doi.org/10.1145/974750.974752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/974750.974752","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-100","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/a2db6f32-4981-42e7-bc38-c4766b17ae0c","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a2db6f32-4981-42e7-bc38-c4766b17ae0c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Buneman, P, Khanna, S, Tajima, K & Tan, W-C 2004, 'Archiving Scientific Data', ACM Transactions on Database Systems, vol. 29, no. 1, pp. 2-42. https://doi.org/10.1145/974750.974752","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/a2db6f32-4981-42e7-bc38-c4766b17ae0c","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a2db6f32-4981-42e7-bc38-c4766b17ae0c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Buneman, P, Khanna, S, Tajima, K & Tan, W-C 2004, 'Archiving Scientific Data', ACM Transactions on Database Systems, vol. 29, no. 1, pp. 2-42. https://doi.org/10.1145/974750.974752","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G197091734","display_name":"CAREER:  Approximability of Combinatorial Optimization Problems","funder_award_id":"0093117","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W171914305","https://openalex.org/W172857819","https://openalex.org/W198528920","https://openalex.org/W1502938876","https://openalex.org/W1533573623","https://openalex.org/W1749554492","https://openalex.org/W1782543227","https://openalex.org/W1827414635","https://openalex.org/W1965014786","https://openalex.org/W1971602700","https://openalex.org/W1975009259","https://openalex.org/W1976373002","https://openalex.org/W1990244497","https://openalex.org/W2021487990","https://openalex.org/W2024797550","https://openalex.org/W2034918969","https://openalex.org/W2035582095","https://openalex.org/W2056859949","https://openalex.org/W2108584692","https://openalex.org/W2130200371","https://openalex.org/W2133319231","https://openalex.org/W2136393336","https://openalex.org/W2142947709","https://openalex.org/W2143275903","https://openalex.org/W2171177618","https://openalex.org/W2202508117","https://openalex.org/W2230830246","https://openalex.org/W2295428206","https://openalex.org/W2628074563","https://openalex.org/W2753710282","https://openalex.org/W2786481595","https://openalex.org/W4213048098","https://openalex.org/W4213149192","https://openalex.org/W4235095233","https://openalex.org/W4239620712","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W7098258546","https://openalex.org/W7097290286","https://openalex.org/W2009907185","https://openalex.org/W7095587540","https://openalex.org/W4387883016","https://openalex.org/W143460964","https://openalex.org/W2144019624","https://openalex.org/W44556617","https://openalex.org/W2397747726","https://openalex.org/W7096995839"],"abstract_inverted_index":{"Archiving":[0],"is":[1,8,31,66,87,117,141,176,231,245],"important":[2],"for":[3,47,299],"scientific":[4,29],"data,":[5],"where":[6,110,187],"it":[7],"necessary":[9],"to":[10,20,60,152,237,294],"record":[11],"all":[12],"past":[13],"versions":[14,81,101,116],"of":[15,50,72,78,82,102,130,143,161,172,185,196,206,228,313],"a":[16,25,34,39,44,123,183,193],"database":[17],"in":[18,33,69,114,177,247,281],"order":[19],"verify":[21],"findings":[22],"based":[23],"upon":[24],"specific":[26,163],"version.":[27],"Much":[28],"data":[30,104,137,240],"held":[32],"hierachical":[35],"format":[36,236],"and":[37,74,132,168,241,269,302],"has":[38],"key":[40],"structure":[41],"that":[42,65,86,181,210,232,273,307],"provides":[43],"canonical":[45],"identification":[46],"each":[48],"element":[49,112],"the":[51,76,83,103,127,148,166,170,202,242,311],"hierarchy.":[52],"In":[53,259],"this":[54],"article,":[55],"we":[56,233,261,288],"exploit":[57],"these":[58],"properties":[59],"develop":[61],"an":[62,111,173,263,295],"archiving":[63,292],"technique":[64,140],"both":[67],"efficient":[68],"its":[70],"use":[71,234],"space":[73,218,282],"preserves":[75],"continuity":[77,129],"elements":[79,131],"through":[80],"database,":[84],"something":[85],"not":[88,214],"provided":[89],"by":[90],"traditional":[91],"minimum-edit-distance":[92],"diff":[93,223],"approaches.":[94,224],"The":[95],"approach":[96,230],"also":[97,208,246,285],"uses":[98],"timestamps.":[99],"All":[100],"are":[105],"merged":[106],"into":[107,135],"one":[108,136],"hierarchy":[109],"appearing":[113],"multiple":[115],"stored":[118],"only":[119],"once":[120],"along":[121],"with":[122,179,201,222],"timestamp.":[124],"By":[125],"identifying":[126],"semantic":[128],"merging":[133],"them":[134],"structure,":[138],"our":[139,211,229,257,267,270,274,291,318],"capable":[142],"providing":[144],"meaningful":[145],"change":[146],"descriptions,":[147],"archive":[149,167,212,244,276],"allows":[150],"us":[151],"easily":[153],"answer":[154],"certain":[155],"temporal":[156,315],"queries":[157,316],"such":[158,188],"as":[159],"retrieval":[160],"any":[162,216],"version":[164],"from":[165],"finding":[169],"history":[171],"element.":[174],"This":[175],"contrast":[178],"approaches":[180],"store":[182],"sequence":[184],"deltas":[186],"operations":[189],"may":[190],"require":[191],"undoing":[192],"large":[194],"number":[195],"changes":[197],"or":[198],"significant":[199,217],"reasoning":[200],"deltas.":[203],"A":[204],"suite":[205],"experiments":[207,271],"demonstrates":[209],"does":[213],"incur":[215],"overhead":[219],"when":[220],"contrasted":[221],"Another":[225],"useful":[226],"property":[227],"XML":[235,250,264],"represent":[238],"hierarchical":[239],"resulting":[243],"XML.":[248],"Hence,":[249],"tools":[251],"can":[252,289,308],"be":[253],"directly":[254],"applied":[255],"on":[256,266,317],"archive.":[258,319],"particular,":[260],"apply":[262],"compressor":[265],"archive,":[268],"show":[272,286],"compressed":[275,278],"outperforms":[277],"diff-based":[279],"repositories":[280],"efficiency.":[283],"We":[284],"how":[287],"extend":[290],"tool":[293],"external":[296],"memory":[297],"archiver":[298],"higher":[300],"scalability":[301],"describe":[303],"various":[304],"index":[305],"structures":[306],"further":[309],"improve":[310],"efficiency":[312],"some":[314]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
