{"id":"https://openalex.org/W1972743486","doi":"https://doi.org/10.1145/1516360.1516470","title":"Efficient provenance storage over nested data collections","display_name":"Efficient provenance storage over nested data collections","publication_year":2009,"publication_date":"2009-03-24","ids":{"openalex":"https://openalex.org/W1972743486","doi":"https://doi.org/10.1145/1516360.1516470","mag":"1972743486"},"language":"en","primary_location":{"id":"doi:10.1145/1516360.1516470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516470","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516470","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009513565","display_name":"Manish Kumar Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Kumar Anand","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014091778","display_name":"Shawn Bowers","orcid":"https://orcid.org/0000-0002-2972-0197"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shawn Bowers","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112454332","display_name":"Timothy McPhillips","orcid":"https://orcid.org/0000-0002-8238-2449"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy McPhillips","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057600294","display_name":"Bertram Lud\u00e4scher","orcid":"https://orcid.org/0000-0001-9140-936X"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bertram Lud\u00e4scher","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"958","last_page":"969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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/T11937","display_name":"Research Data Management Practices","score":0.9919999837875366,"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/workflow","display_name":"Workflow","score":0.8668453097343445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8220784068107605},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.598383903503418},{"id":"https://openalex.org/keywords/software-versioning","display_name":"Software versioning","score":0.5923525094985962},{"id":"https://openalex.org/keywords/storage-model","display_name":"Storage model","score":0.5022869110107422},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.4876753091812134},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.4875161349773407},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.4712446331977844},{"id":"https://openalex.org/keywords/data-model","display_name":"Data model (GIS)","score":0.4425238072872162},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4201432168483734},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39117518067359924},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.16675472259521484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16593888401985168},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12496930360794067}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8668453097343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220784068107605},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.598383903503418},{"id":"https://openalex.org/C198140048","wikidata":"https://www.wikidata.org/wiki/Q10859422","display_name":"Software versioning","level":3,"score":0.5923525094985962},{"id":"https://openalex.org/C2779659223","wikidata":"https://www.wikidata.org/wiki/Q7619926","display_name":"Storage model","level":2,"score":0.5022869110107422},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.4876753091812134},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.4875161349773407},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.4712446331977844},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.4425238072872162},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4201432168483734},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39117518067359924},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.16675472259521484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16593888401985168},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12496930360794067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1516360.1516470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516470","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/1516360.1516470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516470","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516470","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2807560859","display_name":"ITR Collaborative Research:  Enabling the Science Environment for Ecological Knowledge (SEEK)","funder_award_id":"0533368","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2969239778","display_name":null,"funder_award_id":"IIS-0630033OCI-0722079IIS-0612326DBI-0533368","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G3604551404","display_name":"Collaborative Research: Core Database Technologies to Enable the Integration of AToL Information","funder_award_id":"0630033","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4082146771","display_name":"SEI(BIO)+II: A Collaborative Scientific Workflow Environment for Accelerating Genome-Scale Biological Research","funder_award_id":"0612326","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G470685191","display_name":null,"funder_award_id":"IIS-0630033OCI-0722079IIS-0612326DBI-0533368","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G5592364418","display_name":null,"funder_award_id":"IIS-0612326","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5872208256","display_name":"SDCI NMI Improvement: Development of Kepler CORE -- A Comprehensive, Open, Robust, and Extensible Scientific Workflow Infrastructure","funder_award_id":"0722079","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7159133917","display_name":null,"funder_award_id":"DE-FC02-07-ER25811","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G82760813","display_name":null,"funder_award_id":"OCI-0722079","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414727384","display_name":null,"funder_award_id":"OCI-0722079","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8823761842","display_name":null,"funder_award_id":"DBI-0533368","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G99630077","display_name":null,"funder_award_id":"IIS-0630033OCI-0722079IIS-0612326DBI-0533368","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1972743486.pdf","grobid_xml":"https://content.openalex.org/works/W1972743486.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W126044612","https://openalex.org/W1504026549","https://openalex.org/W1525091459","https://openalex.org/W1533573623","https://openalex.org/W1558832481","https://openalex.org/W1569860203","https://openalex.org/W1573128770","https://openalex.org/W1582664144","https://openalex.org/W1692535048","https://openalex.org/W1780933788","https://openalex.org/W1785355888","https://openalex.org/W1821981979","https://openalex.org/W1827414635","https://openalex.org/W1971744183","https://openalex.org/W1983833794","https://openalex.org/W1988545508","https://openalex.org/W1994326726","https://openalex.org/W1996138408","https://openalex.org/W2001176284","https://openalex.org/W2024808072","https://openalex.org/W2027156036","https://openalex.org/W2027172230","https://openalex.org/W2032417141","https://openalex.org/W2048779915","https://openalex.org/W2097284091","https://openalex.org/W2100153179","https://openalex.org/W2100928478","https://openalex.org/W2102717009","https://openalex.org/W2104483974","https://openalex.org/W2104892386","https://openalex.org/W2112525062","https://openalex.org/W2115570304","https://openalex.org/W2124679016","https://openalex.org/W2127279146","https://openalex.org/W2130304121","https://openalex.org/W2138811609","https://openalex.org/W2141306658","https://openalex.org/W2153048220","https://openalex.org/W2155656163","https://openalex.org/W2162192988","https://openalex.org/W2170175479","https://openalex.org/W2203887455","https://openalex.org/W4206031975","https://openalex.org/W4248547660","https://openalex.org/W4300845674","https://openalex.org/W6633513001"],"related_works":["https://openalex.org/W2373541195","https://openalex.org/W2379425324","https://openalex.org/W2376410910","https://openalex.org/W2375552622","https://openalex.org/W2391168633","https://openalex.org/W2365658322","https://openalex.org/W2385499106","https://openalex.org/W2352344200","https://openalex.org/W291310304","https://openalex.org/W2155606843"],"abstract_inverted_index":{"Scientific":[0],"workflow":[1,20,27,42,67,144],"systems":[2,28],"are":[3],"increasingly":[4],"used":[5],"to":[6,13,34,63,114,159],"automate":[7],"complex":[8,70],"data":[9,39,53,68,86,91,106],"analyses,":[10],"largely":[11],"due":[12],"their":[14],"benefits":[15],"over":[16],"traditional":[17],"approaches":[18],"for":[19,103],"design,":[21],"optimization,":[22],"and":[23,59,88,105,111,117,124,132,142,161],"provenance":[24,37,76,119,163],"recording.":[25],"Many":[26],"employ":[29],"a":[30,75],"simple":[31],"dependency":[32],"model":[33,48,94],"represent":[35],"the":[36,79,156],"of":[38],"produced":[40],"by":[41,56],"runs.":[43],"Although":[44],"commonly":[45],"adopted,":[46],"this":[47],"does":[49],"not":[50],"capture":[51],"explicit":[52,85],"dependencies":[54,87],"introduced":[55],"\"provenance-aware\"":[57],"processes,":[58],"it":[60],"can":[61],"lead":[62],"inefficient":[64],"storage":[65,130,151],"when":[66],"is":[69],"or":[71],"structured.":[72],"We":[73,108,136],"present":[74,109],"model,":[77,123],"extending":[78],"conventional":[80],"approach,":[81],"that":[82],"supports":[83],"(i)":[84],"(ii)":[89],"nested":[90],"collections.":[92],"Our":[93],"adopts":[95],"techniques":[96,113],"from":[97],"reference-based":[98],"XML":[99],"versioning,":[100],"adding":[101],"annotations":[102],"process":[104],"dependencies.":[107],"strategies":[110],"reduction":[112],"store":[115,160],"immediate":[116],"transitive":[118],"information":[120],"within":[121],"our":[122,138],"examine":[125],"trade-offs":[126],"among":[127],"update":[128],"time,":[129],"size,":[131,152],"query":[133,162],"response":[134],"time.":[135],"evaluate":[137],"approach":[139],"on":[140],"real-world":[141],"synthetic":[143],"execution":[145],"traces,":[146],"demonstrating":[147],"significant":[148],"reductions":[149],"in":[150],"while":[153],"also":[154],"reducing":[155],"time":[157],"required":[158],"information.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
