{"id":"https://openalex.org/W4389610187","doi":"https://doi.org/10.1145/3626744","title":"Practical Dynamic Extension for Sampling Indexes","display_name":"Practical Dynamic Extension for Sampling Indexes","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389610187","doi":"https://doi.org/10.1145/3626744"},"language":"en","primary_location":{"id":"doi:10.1145/3626744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626744","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"Proceedings of the ACM on Management of Data","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/A5048219741","display_name":"Douglas B. Rumbaugh","orcid":"https://orcid.org/0000-0002-9265-652X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas B. Rumbaugh","raw_affiliation_strings":["Penn State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9265-652X","affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101871030","display_name":"Dong Xie","orcid":"https://orcid.org/0000-0003-4857-900X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Xie","raw_affiliation_strings":["Penn State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4857-900X","affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.5219,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64268724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9980999827384949,"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":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8445283770561218},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7176283597946167},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5735995769500732},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5667270421981812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5615499019622803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5505794882774353},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5390694737434387},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5001358985900879},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44763973355293274},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.42362987995147705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08971196413040161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445283770561218},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7176283597946167},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5735995769500732},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5667270421981812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5615499019622803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5505794882774353},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5390694737434387},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5001358985900879},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44763973355293274},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.42362987995147705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08971196413040161},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626744","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1577072106","https://openalex.org/W1973643480","https://openalex.org/W1998872256","https://openalex.org/W2024859348","https://openalex.org/W2029815943","https://openalex.org/W2042558865","https://openalex.org/W2068739275","https://openalex.org/W2071989194","https://openalex.org/W2092552533","https://openalex.org/W2101196063","https://openalex.org/W2116940697","https://openalex.org/W2119738171","https://openalex.org/W2119885577","https://openalex.org/W2123845384","https://openalex.org/W2152589529","https://openalex.org/W2158194525","https://openalex.org/W2429510775","https://openalex.org/W2436406362","https://openalex.org/W2605800201","https://openalex.org/W2758096189","https://openalex.org/W2798441769","https://openalex.org/W2798891709","https://openalex.org/W2903162282","https://openalex.org/W2948214724","https://openalex.org/W2963192909","https://openalex.org/W2963430603","https://openalex.org/W2966439611","https://openalex.org/W2999362268","https://openalex.org/W3018708672","https://openalex.org/W3030848490","https://openalex.org/W3100965700","https://openalex.org/W3102113847","https://openalex.org/W3175228669","https://openalex.org/W3176757854","https://openalex.org/W3207452942","https://openalex.org/W4244990074","https://openalex.org/W4282600728","https://openalex.org/W4288070772","https://openalex.org/W4313065965","https://openalex.org/W4320838196","https://openalex.org/W4379135640","https://openalex.org/W6959643953"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W1511772879","https://openalex.org/W4200340037","https://openalex.org/W4379115841","https://openalex.org/W608917066","https://openalex.org/W4283652261","https://openalex.org/W585424826","https://openalex.org/W4298250360"],"abstract_inverted_index":{"The":[0,175],"execution":[1],"of":[2,24,27,39,87,211,226,240],"analytical":[3],"queries":[4,41],"on":[5,160],"massive":[6],"datasets":[7],"presents":[8],"challenges":[9],"due":[10],"to":[11,77,98,109,126,139,171,205,214,233],"long":[12],"response":[13],"times":[14],"and":[15,65,101,147,192,208,217],"high":[16,79],"computational":[17],"costs.":[18],"As":[19],"a":[20,91,119,145,168,223],"result,":[21],"the":[22,37,43,53,85,103,172,209,212,228,237],"analysis":[23],"representative":[25],"samples":[26],"data":[28,95,219],"has":[29],"emerged":[30],"as":[31],"an":[32,182],"attractive":[33],"alternative;":[34],"this":[35,71,141,203],"avoids":[36],"cost":[38],"processing":[40],"against":[42],"entire":[44],"dataset,":[45],"while":[46,128,244],"still":[47],"producing":[48],"statistically":[49],"valid":[50],"results.":[51],"Unfortunately,":[52],"sampling":[54,116,122,134,153,190,198,249],"techniques":[55],"in":[56,248],"common":[57],"use":[58],"sacrifice":[59],"either":[60],"sample":[61,81],"quality":[62,80],"or":[63,235],"performance,":[64,189,191],"so":[66,102],"are":[67,124,200,231],"poorly":[68],"suited":[69],"for":[70,150],"task.":[72],"However,":[73],"it":[74],"is":[75,96,112,179,220],"possible":[76],"build":[78],"sets":[82],"efficiently":[83],"with":[84,155,167,181],"assistance":[86],"indexes.":[88],"This":[89,111,136],"introduces":[90],"new":[92],"challenge:":[93],"real-world":[94],"subject":[97],"continuous":[99],"update,":[100,127],"indexes":[104,117,123,131,154,162,199,230],"must":[105],"be":[106],"kept":[107],"up":[108],"date.":[110],"difficult,":[113],"because":[114],"existing":[115,196],"present":[118],"dichotomy;":[120],"efficient":[121,156],"difficult":[125],"easily":[129],"updatable":[130],"have":[132],"poor":[133],"performance.":[135],"paper":[137],"seeks":[138],"address":[140],"gap":[142],"by":[143],"proposing":[144],"general":[146],"practical":[148],"framework":[149,204,213],"extending":[151],"most":[152],"update":[157,188,238],"support,":[158],"based":[159],"splitting":[161],"into":[163],"smaller":[164],"shards,":[165],"combined":[166],"systematic":[169],"approach":[170],"periodic":[173],"reconstruction.":[174],"framework's":[176],"design":[177],"space":[178],"examined,":[180],"eye":[183],"towards":[184],"exploring":[185],"trade-offs":[186],"between":[187],"memory":[193],"usage.":[194],"Three":[195],"static":[197],"extended":[201,229],"using":[202],"support":[206],"updates,":[207],"generalization":[210],"concurrent":[215],"operations":[216],"larger-than-memory":[218],"discussed.":[221],"Through":[222],"comprehensive":[224],"suite":[225],"benchmarks,":[227],"shown":[232],"match":[234],"exceed":[236],"throughput":[239],"state-of-the-art":[241],"dynamic":[242],"baselines,":[243],"presenting":[245],"significant":[246],"improvements":[247],"latency.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}