{"id":"https://openalex.org/W4414427925","doi":"https://doi.org/10.1145/3749163","title":"F3: The Open-Source Data File Format for the Future","display_name":"F3: The Open-Source Data File Format for the Future","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414427925","doi":"https://doi.org/10.1145/3749163"},"language":"en","primary_location":{"id":"doi:10.1145/3749163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3749163","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/10.1145/3749163","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072310638","display_name":"Xinyu Zeng","orcid":"https://orcid.org/0009-0002-6858-1457"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Zeng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046229086","display_name":"Ruijun Meng","orcid":"https://orcid.org/0000-0003-2311-4476"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijun Meng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021820528","display_name":"Martin Prammer","orcid":"https://orcid.org/0009-0000-4348-236X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Prammer","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063728326","display_name":"Wes McKinney","orcid":"https://orcid.org/0000-0003-4028-1639"},"institutions":[{"id":"https://openalex.org/I2802843175","display_name":"University School of Nashville","ror":"https://ror.org/05s409k40","country_code":"US","type":"education","lineage":["https://openalex.org/I2802843175"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wes McKinney","raw_affiliation_strings":["Posit PBC, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Posit PBC, Nashville, TN, USA","institution_ids":["https://openalex.org/I2802843175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049165312","display_name":"Andrew Pavlo","orcid":"https://orcid.org/0000-0001-6040-6991"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Pavlo","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048293406","display_name":"Huanchen Zhang","orcid":"https://orcid.org/0009-0001-4821-1558"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanchen Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China and Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072310638"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.4888,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8714362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983999729156494,"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/file-system","display_name":"File system","score":0.588699996471405},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.5680000185966492},{"id":"https://openalex.org/keywords/computer-file","display_name":"Computer file","score":0.47600001096725464},{"id":"https://openalex.org/keywords/backward-compatibility","display_name":"Backward compatibility","score":0.4675000011920929},{"id":"https://openalex.org/keywords/ssh-file-transfer-protocol","display_name":"SSH File Transfer Protocol","score":0.45989999175071716},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.4327000081539154},{"id":"https://openalex.org/keywords/file-sharing","display_name":"File sharing","score":0.40459999442100525},{"id":"https://openalex.org/keywords/self-certifying-file-system","display_name":"Self-certifying File System","score":0.400299996137619},{"id":"https://openalex.org/keywords/versioning-file-system","display_name":"Versioning file system","score":0.3950999975204468},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C20574231","wikidata":"https://www.wikidata.org/wiki/Q844605","display_name":"Backward compatibility","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C88520388","wikidata":"https://www.wikidata.org/wiki/Q1126823","display_name":"SSH File Transfer Protocol","level":4,"score":0.45989999175071716},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C551386961","wikidata":"https://www.wikidata.org/wiki/Q22666","display_name":"File sharing","level":3,"score":0.40459999442100525},{"id":"https://openalex.org/C82820731","wikidata":"https://www.wikidata.org/wiki/Q2640620","display_name":"Self-certifying File System","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C166807848","wikidata":"https://www.wikidata.org/wiki/Q3445065","display_name":"Versioning file system","level":4,"score":0.3950999975204468},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.3813999891281128},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C26656859","wikidata":"https://www.wikidata.org/wiki/Q4089244","display_name":"File system fragmentation","level":4,"score":0.32170000672340393},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C193769178","wikidata":"https://www.wikidata.org/wiki/Q14679","display_name":"Device file","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C11090531","wikidata":"https://www.wikidata.org/wiki/Q1361922","display_name":"NetCDF","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C58861120","wikidata":"https://www.wikidata.org/wiki/Q1330734","display_name":"Virtual file system","level":5,"score":0.27160000801086426},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2781057727","wikidata":"https://www.wikidata.org/wiki/Q9941","display_name":"Parallel I/O","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3749163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3749163","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:10.1145/3749163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3749163","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":31,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2047474931","https://openalex.org/W2074935284","https://openalex.org/W2110086534","https://openalex.org/W2112735105","https://openalex.org/W2130642985","https://openalex.org/W2172220707","https://openalex.org/W2625141509","https://openalex.org/W2790634852","https://openalex.org/W2798891709","https://openalex.org/W2798926543","https://openalex.org/W2806056912","https://openalex.org/W3013316555","https://openalex.org/W3031206277","https://openalex.org/W3084651990","https://openalex.org/W3085477028","https://openalex.org/W3085940077","https://openalex.org/W4246662059","https://openalex.org/W4286447321","https://openalex.org/W4312429406","https://openalex.org/W4312453576","https://openalex.org/W4376599704","https://openalex.org/W4383749437","https://openalex.org/W4386128176","https://openalex.org/W4386128195","https://openalex.org/W4389539860","https://openalex.org/W4393180321","https://openalex.org/W4399163578","https://openalex.org/W4399163739","https://openalex.org/W4401852864","https://openalex.org/W4404181350"],"related_works":[],"abstract_inverted_index":{"Columnar":[0],"storage":[1,177,211],"formats":[2,16,29,49],"are":[3,42,189],"the":[4,74,87,113,155,167,170,207,214],"foundation":[5],"for":[6,36],"modern":[7],"data":[8,22,126,133,156],"analytics":[9],"systems.":[10],"The":[11],"proliferation":[12],"of":[13,209,216],"open-source":[14,98,201],"file":[15,99,152,174,202],"(i.e.,":[17],"Parquet,":[18],"ORC)":[19],"allows":[20],"seamless":[21],"sharing":[23],"across":[24],"disparate":[25],"platforms.":[26],"However,":[27],"these":[28,48,60],"were":[30],"created":[31],"over":[32],"a":[33,80,96,117,122,132,137],"decade":[34],"ago":[35],"hardware":[37],"and":[38,68,77,104,128,136,157,179,199,213],"workload":[39],"environments":[40],"that":[41],"much":[43],"different":[44],"from":[45],"today.":[46],"Although":[47],"have":[50],"incorporated":[51],"some":[52],"updates":[53],"to":[54,57,59,115,140,143,165],"their":[55],"specification":[56],"adapt":[58],"changes,":[61],"not":[62],"all":[63],"deployments":[64],"support":[65],"those":[66],"modifications,":[67],"too":[69],"often":[70],"systems":[71],"cannot":[72],"overcome":[73],"formats'":[75],"deficiencies":[76],"limitations":[78],"without":[79],"rewrite.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,194],"present":[86],"F":[88],"uture-proof":[89],"File":[90],"Format":[91],"(F3)":[92],"project.":[93],"It":[94],"is":[95],"next-generation":[97],"format":[100,119],"with":[101],"interoperability,":[102],"extensibility,":[103],"efficiency":[105],"as":[106,159,161],"its":[107],"core":[108],"design":[109],"principles.":[110],"F3":[111,151],"obviates":[112],"need":[114],"create":[116],"new":[118,145],"every":[120],"time":[121],"shift":[123],"occurs":[124],"in":[125,172,185],"processing":[127],"computing":[129],"by":[130],"providing":[131],"organization":[134],"structure":[135],"general-purpose":[138],"API":[139],"allow":[141],"developers":[142],"add":[144],"encoding":[146],"schemes":[147],"easily.":[148],"Each":[149],"self-describing":[150],"includes":[153],"both":[154],"meta-data,":[158],"well":[160],"WebAssembly":[162],"(Wasm)":[163],"binaries":[164],"decode":[166],"data.":[168],"Embedding":[169],"decoders":[171,188],"each":[173],"requires":[175],"minimal":[176],"(kilobytes)":[178],"ensures":[180],"compatibility":[181],"on":[182],"any":[183],"platform":[184],"case":[186],"native":[187],"unavailable.":[190],"To":[191],"evaluate":[192],"F3,":[193],"compared":[195],"it":[196],"against":[197],"legacy":[198],"state-of-the-art":[200],"formats.":[203],"Our":[204],"evaluations":[205],"demonstrate":[206],"efficacy":[208],"F3's":[210],"layout":[212],"benefits":[215],"Wasm-driven":[217],"decoding.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
