{"id":"https://openalex.org/W1964941055","doi":"https://doi.org/10.1145/1107499.1107503","title":"Scientific data management in the coming decade","display_name":"Scientific data management in the coming decade","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W1964941055","doi":"https://doi.org/10.1145/1107499.1107503","mag":"1964941055"},"language":"en","primary_location":{"id":"doi:10.1145/1107499.1107503","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1107499.1107503","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 SIGMOD Record","raw_type":"journal-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/A5106823925","display_name":"Jim Gray","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jim Gray","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037593755","display_name":"David T. Liu","orcid":"https://orcid.org/0000-0001-6948-737X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David T. Liu","raw_affiliation_strings":["Berkeley"],"affiliations":[{"raw_affiliation_string":"Berkeley","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057623707","display_name":"M. A. Nieto\u2010Santisteban","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria Nieto-Santisteban","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019891335","display_name":"Alexander S. Szalay","orcid":"https://orcid.org/0000-0002-4108-3282"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Szalay","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055300310","display_name":"David J. DeWitt","orcid":"https://orcid.org/0009-0007-5037-5205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David J. DeWitt","raw_affiliation_strings":["Wisconsin"],"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090010746","display_name":"Gerd Heber","orcid":"https://orcid.org/0000-0002-7577-6140"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerd Heber","raw_affiliation_strings":["Cornell"],"affiliations":[{"raw_affiliation_string":"Cornell","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5106823925"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":19.4348,"has_fulltext":false,"cited_by_count":485,"citation_normalized_percentile":{"value":0.99356099,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"4","first_page":"34","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/haystack","display_name":"Haystack","score":0.9710351228713989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.837785005569458},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.572528600692749},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.541999101638794},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.5380802154541016},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4585343301296234},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4331907629966736},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3532758951187134},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17025011777877808}],"concepts":[{"id":"https://openalex.org/C13424479","wikidata":"https://www.wikidata.org/wiki/Q5687237","display_name":"Haystack","level":2,"score":0.9710351228713989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837785005569458},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.572528600692749},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.541999101638794},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5380802154541016},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4585343301296234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4331907629966736},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3532758951187134},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17025011777877808},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1107499.1107503","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1107499.1107503","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 SIGMOD Record","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1538652242","https://openalex.org/W1713617650","https://openalex.org/W1997020216","https://openalex.org/W2111996486","https://openalex.org/W2122465391","https://openalex.org/W2140332639","https://openalex.org/W2153939720","https://openalex.org/W6632347408"],"related_works":["https://openalex.org/W2135768893","https://openalex.org/W2350545679","https://openalex.org/W4389328405","https://openalex.org/W176219849","https://openalex.org/W3021414116","https://openalex.org/W3012199530","https://openalex.org/W4285821887","https://openalex.org/W2043280262","https://openalex.org/W1949335595","https://openalex.org/W2143693839"],"abstract_inverted_index":{"Scientific":[0],"instruments":[1,31],"and":[2,17,63,77],"computer":[3],"simulations":[4],"are":[5,23],"creating":[6],"vast":[7],"data":[8,36,44],"stores":[9],"that":[10,56,64,82],"require":[11],"new":[12,30],"scientific":[13],"methods":[14],"to":[15,45],"analyze":[16],"organize":[18],"the":[19,35,47,75],"data.":[20],"Data":[21],"volumes":[22],"approximately":[24],"doubling":[25],"each":[26],"year.":[27],"Since":[28],"these":[29],"have":[32],"extraordinary":[33],"precision,":[34],"quality":[37],"is":[38],"also":[39],"rapidly":[40],"improving.":[41],"Analyzing":[42],"this":[43],"find":[46,66],"subtle":[48,68],"effects":[49,69],"missed":[50],"by":[51],"previous":[52,86],"studies":[53],"requires":[54],"algorithms":[55],"can":[57,65],"simultaneously":[58],"deal":[59],"with":[60],"huge":[61],"datasets":[62],"very":[67,79],"---":[70],"finding":[71,78],"both":[72],"needles":[73],"in":[74,85],"haystack":[76],"small":[80],"haystacks":[81],"were":[83],"undetected":[84],"measurements.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":33},{"year":2013,"cited_by_count":38},{"year":2012,"cited_by_count":39}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}