{"id":"https://openalex.org/W4411141403","doi":"https://doi.org/10.1145/3725227","title":"A Theoretical Framework for Distribution-Aware Dataset Search","display_name":"A Theoretical Framework for Distribution-Aware Dataset Search","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411141403","doi":"https://doi.org/10.1145/3725227"},"language":"en","primary_location":{"id":"doi:10.1145/3725227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725227","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/A5114419945","display_name":"Aryan Esmailpour","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aryan Esmailpour","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0009-0000-3798-9578","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"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":"Sainyam Galhotra","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-2529-4036","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043765015","display_name":"Rahul Raychaudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Raychaudhury","raw_affiliation_strings":["Department of Computer Science, Duke University, Durham, NC, USA"],"raw_orcid":"https://orcid.org/0009-0009-6610-4404","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015883931","display_name":"Stavros Sintos","orcid":"https://orcid.org/0000-0002-2114-8886"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Sintos","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-2114-8886","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13043713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"2","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":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.583677351474762},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4654228389263153},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3696032464504242},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3594721853733063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1466914713382721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.583677351474762},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4654228389263153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3696032464504242},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3594721853733063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1466914713382721},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725227","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1577072106","https://openalex.org/W1579803282","https://openalex.org/W1984079283","https://openalex.org/W1994664542","https://openalex.org/W2039797405","https://openalex.org/W2042364367","https://openalex.org/W2062831005","https://openalex.org/W2083694582","https://openalex.org/W2129332419","https://openalex.org/W2139959487","https://openalex.org/W2156887552","https://openalex.org/W2426976336","https://openalex.org/W2680551515","https://openalex.org/W2782288225","https://openalex.org/W2810954846","https://openalex.org/W2926805670","https://openalex.org/W3014616325","https://openalex.org/W3032215537","https://openalex.org/W3093315172","https://openalex.org/W3133750907","https://openalex.org/W3139669840","https://openalex.org/W3164968002","https://openalex.org/W3167683174","https://openalex.org/W3196867679","https://openalex.org/W3196904276","https://openalex.org/W3197182341","https://openalex.org/W4210631930","https://openalex.org/W4220820301","https://openalex.org/W4238284510","https://openalex.org/W4251334431","https://openalex.org/W4251391716","https://openalex.org/W4254343065","https://openalex.org/W4283383705","https://openalex.org/W4285451384","https://openalex.org/W4289533971","https://openalex.org/W4299431800","https://openalex.org/W4299841484","https://openalex.org/W4312450986","https://openalex.org/W4365600826","https://openalex.org/W4379135743","https://openalex.org/W4385281886","https://openalex.org/W4386128217","https://openalex.org/W4388125275","https://openalex.org/W4399156240","https://openalex.org/W4399175194","https://openalex.org/W4402042501","https://openalex.org/W6617901010","https://openalex.org/W6661805920","https://openalex.org/W6687876214","https://openalex.org/W6734655831","https://openalex.org/W6740848938","https://openalex.org/W6749511090","https://openalex.org/W6774873859","https://openalex.org/W6775487770","https://openalex.org/W6778630101","https://openalex.org/W6794093957","https://openalex.org/W6851767804","https://openalex.org/W6852139540","https://openalex.org/W6859999024"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Effective":[0],"data":[1,41,63,177,222,305,316,328,351],"discovery":[2,42,64],"is":[3,97,147,173,218,266,346,394,401],"a":[4,81,98,141,148,176,182,221,227,354],"cornerstone":[5],"of":[6,37,83,151,158,270,276,356,390,404],"modern":[7],"data-driven":[8],"decision-making.":[9],"Yet,":[10],"identifying":[11],"datasets":[12,130],"with":[13,307,330],"specific":[14],"distributional":[15],"characteristics,":[16],"such":[17,86,179,195,224,241,359],"as":[18],"percentiles":[19],"or":[20],"preferences,":[21],"remains":[22],"challenging.":[23],"While":[24],"recent":[25],"proposals":[26],"have":[27],"enabled":[28],"users":[29],"to":[30,128,174,219,386],"search":[31],"based":[32],"on":[33,44,279,314],"percentile":[34],"predicates,":[35],"much":[36],"the":[38,56,102,108,114,117,121,129,135,156,168,171,213,216,267,271,289,295,347,368,383,402,405],"research":[39],"in":[40,50,131,294,321,341],"relies":[43],"heuristic":[45],"methods,":[46],"which":[47,146],"often":[48],"result":[49],"biased":[51],"outcomes.":[52],"This":[53],"paper":[54],"presents":[55],"first":[57,284],"theoretically":[58],"backed":[59],"framework":[60],"that":[61,87,154,180,196,225,242,299,334,366],"unifies":[62],"under":[65,113],"centralized":[66,115,122,296],"and":[67,107,116,187,201,233,247,291,338,373,399],"decentralized":[68],"settings.":[69,323],"More":[70],"specifically,":[71],"let":[72],"P":[73,77,89,132,144,152,159,277,364,380],"={P":[74],"1":[75],",...,":[76],"N":[78,84],"}":[79],"be":[80],"repository":[82],"datasets,":[85],"each":[88],"i":[90,145,153,160,164,365,370],"\u2282":[91],"\u211d":[92],"d":[93,96],",":[94,161],"where":[95,258,344,392],"constant.":[99],"We":[100,283,324],"study":[101],"percentile-aware":[103],"indexing":[104,110],"(Ptile)":[105],"problem":[106,112],"preference-aware":[109],"(Pref)":[111],"federated":[118,136],"setting.":[119],"In":[120,134],"setting,":[123,297],"we":[124,138,300,312],"assume":[125],"direct":[126],"access":[127],".":[133,282],"setting":[137],"are":[139],"given":[140,181,226],"synopsis":[142],"S":[143],"compressed":[149],"representation":[150],"captures":[155],"structure":[157,178,223],"for":[162,288,303,318,362],"every":[163,363],"\u2208":[165,198,210,244,371,377],"[N].":[166,211],"For":[167,212],"Ptile":[169,214,290,337],"problem,":[170,215],"goal":[172,217],"construct":[175,220],"predicate":[183,228,384],"(query":[184,229],"rectangle":[185],"R":[186],"an":[188,234,387,395],"interval":[189,235],"\u03b8)":[190,236],"report":[191,237],"all":[192,238],"indexes":[193,239,357],"J":[194,199,240,245,358,372,378],"j":[197,205,208,243,253,262,278,376,381],"if":[200,203,246,249,375],"only":[202,248],"|P":[204],"\u2229":[206],"R|/|P":[207],"|":[209],"vector":[230],"v":[231,280],"\u2192":[232,255,264,281],"\u03c9":[250,259],"k":[251,260,272],"(P":[252],",v":[254,263],")\u2208":[256],"\u03b8,":[257],"(p":[261],")":[265],"score":[268],"(inner-product)":[269],"-th":[273],"largest":[274],"projection":[275],"show":[285,325],"lower":[286],"bounds":[287],"Pref":[292,339],"problems":[293,320],"showing":[298],"cannot":[301],"hope":[302],"near-linear":[304],"structures":[306,317,329,352],"polylogarithmic":[308],"query":[309],"time.":[310],"Then":[311],"focus":[313],"approximate":[315],"both":[319,322],"\u00d8(N)":[326,331],"space":[327],"preprocessing":[332],"time,":[333,343],"can":[335],"answer":[336],"queries":[340],"\u00d8(1+OUT)":[342],"OUT":[345],"output":[348],"size.":[349],"The":[350],"return":[353],"set":[355],"that:":[360],"i)":[361],"satisfies":[367,382],"predicate,":[369],"ii)":[374],"then":[379],"up":[385],"additive":[388],"error":[389,403],"\u03b5+2\u03b4,":[391],"\u03b5":[393],"arbitrarily":[396],"small":[397],"constant":[398],"\u03b4":[400],"synopses.":[406]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}