{"id":"https://openalex.org/W2131215778","doi":"https://doi.org/10.1145/1188455.1188562","title":"Data management and query---Estimating query result sizes for proxy caching in scientific database federations","display_name":"Data management and query---Estimating query result sizes for proxy caching in scientific database federations","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2131215778","doi":"https://doi.org/10.1145/1188455.1188562","mag":"2131215778"},"language":"en","primary_location":{"id":"doi:10.1145/1188455.1188562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071436717","display_name":"Tanu Malik","orcid":"https://orcid.org/0009-0007-9656-727X"},"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":"Tanu Malik","raw_affiliation_strings":["Johns Hopkins University, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084849539","display_name":"Randal Burns","orcid":"https://orcid.org/0000-0002-2924-1997"},"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":"Randal Burns","raw_affiliation_strings":["Johns Hopkins University, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068157871","display_name":"Nitesh V. Chawla","orcid":"https://orcid.org/0000-0003-3932-5956"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitesh V. Chawla","raw_affiliation_strings":["Univ of Notre Dame, Notre Dame, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ of Notre Dame, Notre Dame, IN","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","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, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9401,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7391174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8626251816749573},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6516196727752686},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6410384178161621},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5134290456771851},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49780726432800293},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.48323187232017517},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.45781460404396057},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.41895899176597595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3204106390476227},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.25471365451812744},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18466925621032715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08795168995857239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626251816749573},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6516196727752686},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6410384178161621},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5134290456771851},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49780726432800293},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.48323187232017517},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.45781460404396057},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.41895899176597595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3204106390476227},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.25471365451812744},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18466925621032715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08795168995857239}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1188455.1188562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W141765838","https://openalex.org/W171513795","https://openalex.org/W1487093789","https://openalex.org/W1504694836","https://openalex.org/W1585610988","https://openalex.org/W1918432491","https://openalex.org/W1968403101","https://openalex.org/W1972223681","https://openalex.org/W1998244781","https://openalex.org/W1999749646","https://openalex.org/W2011679994","https://openalex.org/W2016758618","https://openalex.org/W2052797085","https://openalex.org/W2060091058","https://openalex.org/W2065311396","https://openalex.org/W2065871817","https://openalex.org/W2084961399","https://openalex.org/W2090336890","https://openalex.org/W2097706874","https://openalex.org/W2101416352","https://openalex.org/W2102166438","https://openalex.org/W2104506262","https://openalex.org/W2110557355","https://openalex.org/W2110849300","https://openalex.org/W2120108467","https://openalex.org/W2125055259","https://openalex.org/W2129660602","https://openalex.org/W2135252439","https://openalex.org/W2138752345","https://openalex.org/W2138793904","https://openalex.org/W2150753219","https://openalex.org/W2151310484","https://openalex.org/W2153329411","https://openalex.org/W2171903035","https://openalex.org/W2212047990","https://openalex.org/W3099250505"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2572349046","https://openalex.org/W2026738364","https://openalex.org/W2901901036","https://openalex.org/W3125756434","https://openalex.org/W2146885082","https://openalex.org/W2100181111","https://openalex.org/W3049728138","https://openalex.org/W8514837","https://openalex.org/W2184296057"],"abstract_inverted_index":{"In":[0],"a":[1,17,21,53],"proxy":[2,69,106],"cache":[3,28,42,107,134],"for":[4,56],"federations":[5],"of":[6,16,68,75,87,108,115],"scientific":[7],"databases":[8],"it":[9],"is":[10,62],"important":[11],"to":[12,64],"estimate":[13],"the":[14,34,41,65,72,85,105,109,121],"size":[15],"query":[18,58,80,88],"before":[19],"making":[20],"caching":[22],"decision.":[23],"With":[24],"accurate":[25],"estimates,":[26],"near-optimal":[27,133],"performance":[29],"can":[30,39],"be":[31],"obtained.":[32],"On":[33],"other":[35],"extreme,":[36],"inaccurate":[37],"estimates":[38,79],"render":[40],"totally":[43],"ineffective.":[44],"We":[45,100],"present":[46],"classification":[47],"and":[48,71,131],"regression":[49],"over":[50],"templates":[51],"(CAROT),":[52],"general":[54],"method":[55],"estimating":[57],"result":[59,81],"sizes,":[60],"which":[61],"suited":[63],"resource-limited":[66],"environment":[67],"caches":[70],"distributed":[73],"nature":[74],"database":[76],"federations.":[77],"CAROT":[78,103,125],"sizes":[82],"by":[83,91],"learning":[84],"distribution":[86],"results,":[89],"not":[90],"examining":[92],"or":[93],"sampling":[94],"data,":[95],"but":[96],"from":[97],"observing":[98],"workload.":[99],"have":[101],"integrated":[102],"into":[104],"National":[110],"Virtual":[111],"Observatory":[112],"(NVO)":[113],"federation":[114],"astronomy":[116],"databases.":[117],"Experiments":[118],"conducted":[119],"in":[120],"NVO":[122],"show":[123],"that":[124],"dramatically":[126],"outperforms":[127],"conventional":[128],"estimation":[129],"techniques":[130],"provides":[132],"performance.":[135]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}