{"id":"https://openalex.org/W2058874014","doi":"https://doi.org/10.1109/icde.2010.5447879","title":"PIP: A database system for great and small expectations","display_name":"PIP: A database system for great and small expectations","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2058874014","doi":"https://doi.org/10.1109/icde.2010.5447879","mag":"2058874014"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/166833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071259962","display_name":"Oliver Kennedy","orcid":"https://orcid.org/0000-0003-0632-1668"},"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":true,"raw_author_name":"Oliver Kennedy","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY, USA","[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101903922","display_name":"Christoph Koch","orcid":"https://orcid.org/0000-0002-9130-7205"},"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":"Christoph Koch","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY, USA","[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071259962"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":5.4109,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96253017,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692422866821289},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7407216429710388},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6740984916687012},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5886122584342957},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5829659700393677},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.5428024530410767},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.5087535977363586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.491091251373291},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48687639832496643},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4866383969783783},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.47519242763519287},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4548318088054657},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43649935722351074},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.36087566614151},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.342305064201355},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3299259841442108},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29294148087501526},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.20983678102493286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20016014575958252},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.1766534447669983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1717272698879242},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.16863834857940674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16633006930351257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692422866821289},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7407216429710388},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6740984916687012},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5886122584342957},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5829659700393677},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.5428024530410767},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.5087535977363586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.491091251373291},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48687639832496643},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4866383969783783},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.47519242763519287},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4548318088054657},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43649935722351074},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.36087566614151},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.342305064201355},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3299259841442108},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29294148087501526},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.20983678102493286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20016014575958252},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.1766534447669983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1717272698879242},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.16863834857940674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16633006930351257},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icde.2010.5447879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.42","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.42","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/~koch/download/icde2010_pip.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:166833","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/166833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:166833","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/166833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W274239259","https://openalex.org/W1990391007","https://openalex.org/W2016443758","https://openalex.org/W2051203581","https://openalex.org/W2056760934","https://openalex.org/W2065538099","https://openalex.org/W2078686663","https://openalex.org/W2088422262","https://openalex.org/W2114157818","https://openalex.org/W2116832440","https://openalex.org/W2120825705","https://openalex.org/W2130416410","https://openalex.org/W2140481308","https://openalex.org/W2143485006","https://openalex.org/W2144562386","https://openalex.org/W2144810465","https://openalex.org/W2151322578","https://openalex.org/W2165211504","https://openalex.org/W2167445567","https://openalex.org/W2171776999","https://openalex.org/W2181455273","https://openalex.org/W2296677182","https://openalex.org/W2910407761","https://openalex.org/W4237826793","https://openalex.org/W6634462505","https://openalex.org/W6666720238"],"related_works":["https://openalex.org/W3125756434","https://openalex.org/W2554271401","https://openalex.org/W2912995176","https://openalex.org/W2360617161","https://openalex.org/W1971797742","https://openalex.org/W1716383435","https://openalex.org/W1986707023","https://openalex.org/W1606829490","https://openalex.org/W2111392287","https://openalex.org/W2545191987"],"abstract_inverted_index":{"Estimation":[0],"via":[1],"sampling":[2,22,141,178],"out":[3],"of":[4,27,63,91,105,111,146,161,177,185,197,213,220],"highly":[5,221],"selective":[6,222],"join":[7,223],"queries":[8],"is":[9,53,124,129],"well":[10,150],"known":[11],"to":[12,60,84,108,121,132,167],"be":[13,77,85,122],"problematic,":[14],"most":[15,165],"notably":[16],"in":[17,45,217],"online":[18],"aggregation.":[19],"Without":[20],"goal-directed":[21],"strategies,":[23],"samples":[24,64,74],"falling":[25],"outside":[26],"the":[28,67,69,119,159,162,168,175,183,198,209,218],"selection":[29,160],"constraints":[30],"lower":[31],"estimation":[32],"efficiency":[33,210],"at":[34,40],"best,":[35],"and":[36,114,136,172,211],"cause":[37],"inaccurate":[38],"estimates":[39],"worst":[41],"This":[42,127],"problem":[43],"appears":[44],"general":[46,97,131],"probabilistic":[47,98,106],"database":[48,99],"systems,":[49],"where":[50],"query":[51,79],"processing":[52,80],"tightly":[54],"coupled":[55],"with":[56],"sampling.":[57],"By":[58],"committing":[59],"a":[61,96,143,204],"set":[62],"before":[65],"evaluating":[66],"query,":[68],"engine":[70],"wastes":[71],"effort":[72],"on":[73,208],"that":[75,81,101,190],"will":[76],"discarded,":[78],"may":[82],"need":[83],"repeated,":[86],"or":[87],"unnecessarily":[88],"large":[89],"numbers":[90],"samples.":[92],"We":[93,181],"describe":[94],"PIP,":[95],"system":[100],"uses":[102],"symbolic":[103],"representations":[104],"data":[107],"defer":[109],"computation":[110],"expectations,":[112,157],"moments,":[113],"other":[115],"statistical":[116],"measures":[117],"until":[118],"expression":[120,169],"measured":[123],"fully":[125],"known.":[126],"approach":[128,187],"sufficiently":[130],"admit":[133],"both":[134],"continuous":[135],"discrete":[137],"distributions.":[138],"Moreover,":[139],"deferring":[140],"enables":[142],"broad":[144],"range":[145],"goal-oriented":[147],"sampling-based":[148],"(as":[149],"as":[151],"exact)":[152],"integration":[153,163],"techniques":[154],"for":[155],"computing":[156],"allows":[158],"strategy":[164],"appropriate":[166],"being":[170],"measured,":[171],"can":[173,194],"reduce":[174],"amount":[176],"work":[179],"required.":[180],"demonstrate":[182],"effectiveness":[184],"this":[186],"by":[188],"showing":[189],"even":[191],"straightforward":[192],"algorithms":[193,202],"make":[195],"use":[196],"added":[199],"information.":[200],"These":[201],"have":[203],"profoundly":[205],"positive":[206],"impact":[207],"accuracy":[212],"expectation":[214],"computations,":[215],"particularly":[216],"case":[219],"queries.":[224]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}