{"id":"https://openalex.org/W4411403517","doi":"https://doi.org/10.1145/3725329","title":"Nested Parquet Is Flat, Why Not Use It? How To Scan Nested Data With On-the-Fly Key Generation and Joins","display_name":"Nested Parquet Is Flat, Why Not Use It? How To Scan Nested Data With On-the-Fly Key Generation and Joins","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403517","doi":"https://doi.org/10.1145/3725329"},"language":"en","primary_location":{"id":"doi:10.1145/3725329","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3725329","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118331009","display_name":"Alice Rey","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alice Rey","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0002-9210-4124","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118331010","display_name":"Maximilian Rieger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Rieger","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0007-8887-2960","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880157","display_name":"Thomas Neumann","orcid":"https://orcid.org/0000-0001-5787-142X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Neumann","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5787-142X","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.9389,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76509737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/joins","display_name":"Joins","score":0.8684663772583008},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923806071281433},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6640143394470215},{"id":"https://openalex.org/keywords/nesting","display_name":"Nesting (process)","score":0.657467782497406},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5549717545509338},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5003354549407959},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.46653276681900024},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43587806820869446},{"id":"https://openalex.org/keywords/nested-set-model","display_name":"Nested set model","score":0.4248626232147217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21834874153137207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14947155117988586},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1349831223487854}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8684663772583008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923806071281433},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6640143394470215},{"id":"https://openalex.org/C2776937656","wikidata":"https://www.wikidata.org/wiki/Q2229669","display_name":"Nesting (process)","level":2,"score":0.657467782497406},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5549717545509338},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5003354549407959},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.46653276681900024},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43587806820869446},{"id":"https://openalex.org/C103000020","wikidata":"https://www.wikidata.org/wiki/Q1978426","display_name":"Nested set model","level":3,"score":0.4248626232147217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21834874153137207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14947155117988586},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1349831223487854},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725329","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3725329","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1527872672","https://openalex.org/W2007074710","https://openalex.org/W2074935284","https://openalex.org/W2104476081","https://openalex.org/W2107907225","https://openalex.org/W2125529470","https://openalex.org/W2137924956","https://openalex.org/W2230830246","https://openalex.org/W2252077026","https://openalex.org/W2265297126","https://openalex.org/W2406955896","https://openalex.org/W2627491027","https://openalex.org/W2949054050","https://openalex.org/W3085940077","https://openalex.org/W3124246886","https://openalex.org/W3126979860","https://openalex.org/W3176391989","https://openalex.org/W3216464615","https://openalex.org/W4287599870","https://openalex.org/W4376599704","https://openalex.org/W4381329140","https://openalex.org/W4386128176","https://openalex.org/W4389539860","https://openalex.org/W4399163753","https://openalex.org/W6785446530"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2107115321","https://openalex.org/W2114111204","https://openalex.org/W2047453522","https://openalex.org/W4205379036","https://openalex.org/W2800910233","https://openalex.org/W1841066643","https://openalex.org/W1510134535","https://openalex.org/W2171487662","https://openalex.org/W1979093255"],"abstract_inverted_index":{"Parquet":[0,84,108,146],"is":[1,69,123],"the":[2,97,107,113,121],"most":[3],"commonly":[4],"used":[5],"file":[6,75],"format":[7,17,102],"to":[8,60,81,142],"store":[9,93],"data":[10,22,37,67,98],"in":[11,23,71,99],"a":[12,57,94,164],"columnar,":[13],"binary":[14],"structure.":[15],"The":[16],"also":[18],"supports":[19],"storing":[20],"nested":[21,36,66,83,145],"this":[24,49,53,72],"flattened":[25],"columnar":[26,74],"layout.":[27],"However,":[28],"many":[29],"query":[30,63,111,140,156],"engines":[31,64,141],"either":[32],"do":[33],"not":[34,92],"support":[35,143],"or":[38],"process":[39,82],"it":[40,163],"with":[41,127],"substantially":[42],"worse":[43],"performance":[44,157],"than":[45,158],"relational":[46,62],"data.":[47],"In":[48],"work,":[50],"we":[51,78,149],"close":[52],"gap":[54],"and":[55,120],"present":[56],"new":[58],"way":[59],"leverage":[61],"for":[65],"that":[68],"stored":[70],"flat":[73,115],"format.":[76],"Specifically,":[77],"demonstrate":[79],"how":[80],"files":[85],"much":[86],"more":[87],"efficiently.":[88],"Our":[89,132],"approach":[90,133],"does":[91],"copy":[95],"of":[96,152],"an":[100],"internal":[101],"but":[103],"reads":[104],"directly":[105],"from":[106],"file.":[109],"During":[110],"computation,":[112],"required":[114],"columns":[116],"are":[117],"scanned":[118],"independently":[119],"nesting":[122],"reconstructed":[124],"using":[125],"joins":[126],"on-the-fly":[128],"generated":[129],"join":[130],"keys.":[131],"can":[134],"be":[135],"easily":[136],"integrated":[137],"into":[138],"existing":[139,159],"querying":[144],"files.":[147],"Furthermore,":[148],"achieve":[150],"orders":[151],"magnitude":[153],"faster":[154],"analytical":[155],"solutions,":[160],"which":[161],"makes":[162],"valuable":[165],"addition.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
