{"id":"https://openalex.org/W4398234834","doi":"https://doi.org/10.1145/3626246.3653368","title":"Apache Arrow DataFusion: A Fast, Embeddable, Modular Analytic Query Engine","display_name":"Apache Arrow DataFusion: A Fast, Embeddable, Modular Analytic Query Engine","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398234834","doi":"https://doi.org/10.1145/3626246.3653368"},"language":"en","primary_location":{"id":"doi:10.1145/3626246.3653368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-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/A5072722765","display_name":"Andrew Lamb","orcid":"https://orcid.org/0009-0004-5687-5276"},"institutions":[{"id":"https://openalex.org/I4210137206","display_name":"Influx (United States)","ror":"https://ror.org/041yzwn62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137206"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Lamb","raw_affiliation_strings":["InfluxData, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"InfluxData, Boston, MA, USA","institution_ids":["https://openalex.org/I4210137206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017014737","display_name":"Yijie Shen","orcid":"https://orcid.org/0000-0002-2679-1088"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijie Shen","raw_affiliation_strings":["Space and Time, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Space and Time, Irvine, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098770336","display_name":"Dani\u00ebl Heres","orcid":"https://orcid.org/0009-0009-3087-4992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dani\u00ebl Heres","raw_affiliation_strings":["Coralogix, Utrecht, Netherlands"],"affiliations":[{"raw_affiliation_string":"Coralogix, Utrecht, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081137168","display_name":"Jayjeet Chakraborty","orcid":"https://orcid.org/0000-0003-1647-2494"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayjeet Chakraborty","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098770337","display_name":"Mehmet Ozan Kabak","orcid":"https://orcid.org/0009-0000-5425-2834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehmet Ozan Kabak","raw_affiliation_strings":["Synnada, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Synnada, Austin, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067241596","display_name":"Liang-Chi Hsieh","orcid":"https://orcid.org/0009-0002-6513-984X"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang-Chi Hsieh","raw_affiliation_strings":["Apple, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081304869","display_name":"Chao Sun","orcid":"https://orcid.org/0009-0000-8192-3496"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Sun","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072722765"],"corresponding_institution_ids":["https://openalex.org/I4210137206"],"apc_list":null,"apc_paid":null,"fwci":2.7919,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90750444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"17"},"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":0.9976999759674072,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7445186972618103},{"id":"https://openalex.org/keywords/arrow","display_name":"Arrow","score":0.7360963225364685},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6168332695960999},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4369688034057617},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4121802747249603},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29227739572525024},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2835926413536072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445186972618103},{"id":"https://openalex.org/C2780339515","wikidata":"https://www.wikidata.org/wiki/Q3074698","display_name":"Arrow","level":2,"score":0.7360963225364685},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6168332695960999},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4369688034057617},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4121802747249603},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29227739572525024},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2835926413536072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626246.3653368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626246.3653368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1519039476","https://openalex.org/W1521148341","https://openalex.org/W1974796034","https://openalex.org/W1999883293","https://openalex.org/W2006296837","https://openalex.org/W2074935284","https://openalex.org/W2091362119","https://openalex.org/W2099035968","https://openalex.org/W2126583885","https://openalex.org/W2144839430","https://openalex.org/W2260671045","https://openalex.org/W2542459869","https://openalex.org/W2806617922","https://openalex.org/W2903257396","https://openalex.org/W2925032266","https://openalex.org/W2949054050","https://openalex.org/W3085477028","https://openalex.org/W4244768633","https://openalex.org/W4282585030","https://openalex.org/W4285160575","https://openalex.org/W4291713239","https://openalex.org/W4312292115","https://openalex.org/W4385653242","https://openalex.org/W6969259846"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1437213286","https://openalex.org/W3149432069","https://openalex.org/W2083151571","https://openalex.org/W2011564139","https://openalex.org/W102771113","https://openalex.org/W2403473672","https://openalex.org/W1901793333","https://openalex.org/W2460650438"],"abstract_inverted_index":{"Apache":[0,16],"Arrow":[1,17],"DataFusion":[2],"is":[3,32],"a":[4,88],"fast,":[5],"embeddable,":[6],"and":[7,34,50,79],"extensible":[8,80],"query":[9],"engine":[10],"written":[11],"in":[12,38],"Rust":[13],"that":[14],"uses":[15],"as":[18,63,65],"its":[19,46],"memory":[20],"model.":[21],"In":[22],"this":[23],"paper":[24],"we":[25,75],"describe":[26],"the":[27,55,66],"technologies":[28],"on":[29],"which":[30],"it":[31,36],"built,":[33],"how":[35],"fits":[37],"long-term":[39],"database":[40],"implementation":[41],"trends.":[42],"We":[43],"then":[44],"enumerate":[45],"features,":[47],"optimizations,":[48],"architecture":[49],"extension":[51],"APIs":[52],"to":[53,93],"illustrate":[54],"breadth":[56],"of":[57,59,90],"requirements":[58],"modern":[60],"OLAP":[61],"engines":[62],"well":[64],"interfaces":[67],"needed":[68],"by":[69],"systems":[70],"built":[71],"with":[72],"them.":[73],"Finally,":[74],"demonstrate":[76],"open":[77],"standards":[78],"design":[81],"do":[82],"not":[83],"preclude":[84],"state-of-the-art":[85],"performance":[86],"using":[87],"series":[89],"experimental":[91],"comparisons":[92],"DuckDB.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
