{"id":"https://openalex.org/W4414266791","doi":"https://doi.org/10.14778/3750601.3750636","title":"Ursa: A Lakehouse-Native Data Streaming Engine for Kafka","display_name":"Ursa: A Lakehouse-Native Data Streaming Engine for Kafka","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414266791","doi":"https://doi.org/10.14778/3750601.3750636"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750636","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750636","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","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/A5119645450","display_name":"Matteo Merli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140560","display_name":"National Council for Air and Stream Improvement","ror":"https://ror.org/03xcfma33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Merli","raw_affiliation_strings":["StreamNative, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StreamNative, Inc","institution_ids":["https://openalex.org/I4210140560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119645451","display_name":"Sijie Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140560","display_name":"National Council for Air and Stream Improvement","ror":"https://ror.org/03xcfma33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sijie Guo","raw_affiliation_strings":["StreamNative, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StreamNative, Inc","institution_ids":["https://openalex.org/I4210140560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119645452","display_name":"Penghui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140560","display_name":"National Council for Air and Stream Improvement","ror":"https://ror.org/03xcfma33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Penghui Li","raw_affiliation_strings":["StreamNative, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StreamNative, Inc","institution_ids":["https://openalex.org/I4210140560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119645453","display_name":"Hang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140560","display_name":"National Council for Air and Stream Improvement","ror":"https://ror.org/03xcfma33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["StreamNative, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StreamNative, Inc","institution_ids":["https://openalex.org/I4210140560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119645454","display_name":"Neng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140560","display_name":"National Council for Air and Stream Improvement","ror":"https://ror.org/03xcfma33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neng Lu","raw_affiliation_strings":["StreamNative, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StreamNative, Inc","institution_ids":["https://openalex.org/I4210140560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210140560"],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89642434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"18","issue":"12","first_page":"5184","last_page":"5196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9527999758720398,"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"}},"topics":[{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9527999758720398,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9271000027656555,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9182999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bespoke","display_name":"Bespoke","score":0.5992000102996826},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5453000068664551},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49630001187324524},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.4147999882698059},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.32659998536109924},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.3019999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254999876022339},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750636","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750636","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3085477028","https://openalex.org/W4254234063"],"related_works":[],"abstract_inverted_index":{"Data":[0],"lakehouse":[1,109],"architectures":[2],"unify":[3],"the":[4,10,40,145,155],"cost-efficiency":[5],"of":[6,13,147,154],"data":[7,14,53,105],"lakes":[8],"with":[9,30],"transactional":[11],"guarantees":[12],"warehouses.":[15],"Yet,":[16],"real-time":[17],"ingestion":[18,68],"often":[19],"depends":[20],"on":[21,111],"external":[22,122],"streaming":[23,54,101,137],"systems":[24],"such":[25],"as":[26],"Apache":[27],"Kafka,":[28],"along":[29],"bespoke":[31],"connectors":[32],"that":[33,103,142],"read":[34],"from":[35],"Kafka":[36,149],"and":[37,45,88,99,121,135],"write":[38],"into":[39],"lakehouse\u2014leading":[41],"to":[42,84,107,159],"increased":[43],"complexity":[44],"high":[46,131],"operational":[47],"costs.":[48],"In":[49],"particular,":[50],"traditional":[51,148],"leader-based":[52,116],"platforms":[55],"are":[56],"designed":[57],"for":[58,66],"sub-100":[59],"ms":[60],"low-latency":[61],"workloads;":[62],"however,":[63],"when":[64],"used":[65],"data-intensive":[67],"in":[69,163],"a":[70,96,152,160],"cloud":[71],"environment,":[72],"cross":[73],"availability-zone":[74],"(AZ)":[75],"disk-based":[76,118],"replication":[77],"significantly":[78],"raises":[79],"total":[80],"infrastructure":[81,127,164],"costs":[82,128],"due":[83],"excessive":[85],"network":[86],"traffic":[87],"overprovisioned":[89],"disk":[90],"storage.":[91,113],"This":[92],"paper":[93],"introduces":[94],"Ursa,":[95],"leaderless,":[97],"cloud-native,":[98],"Kafka-compatible":[100],"engine":[102],"writes":[104],"directly":[106],"open":[108],"tables":[110],"object":[112],"By":[114],"eliminating":[115],"replication,":[117],"broker":[119],"storage,":[120],"connectors,":[123],"Ursa":[124,143],"markedly":[125],"reduces":[126],"while":[129],"preserving":[130],"throughput,":[132],"exactly-once":[133],"semantics,":[134],"near-real-time":[136],"capabilities.":[138],"Experimental":[139],"results":[140],"show":[141],"matches":[144],"performance":[146],"clusters":[150],"at":[151],"fraction":[153],"cost,":[156],"offering":[157],"up":[158],"10x":[161],"reduction":[162],"expenses.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
