{"id":"https://openalex.org/W4400910009","doi":"https://doi.org/10.1109/icde60146.2024.00471","title":"Data Lakes: A Survey of Functions and Systems (Extended abstract)","display_name":"Data Lakes: A Survey of Functions and Systems (Extended abstract)","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4400910009","doi":"https://doi.org/10.1109/icde60146.2024.00471"},"language":"en","primary_location":{"id":"doi:10.1109/icde60146.2024.00471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046074866","display_name":"Rihan Hai","orcid":"https://orcid.org/0000-0002-3720-6585"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rihan Hai","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144380","display_name":"Christos Koutras","orcid":"https://orcid.org/0000-0003-3015-154X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christos Koutras","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043782050","display_name":"Christoph Quix","orcid":"https://orcid.org/0000-0002-1698-4345"},"institutions":[{"id":"https://openalex.org/I4210113269","display_name":"Hochschule Niederrhein","ror":"https://ror.org/027b9qx26","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210113269"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Quix","raw_affiliation_strings":["Hochschule Niederrhein"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hochschule Niederrhein","institution_ids":["https://openalex.org/I4210113269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026501367","display_name":"Matthias Jarke","orcid":"https://orcid.org/0000-0001-6169-2942"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Jarke","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3562,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78828721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5679","last_page":"5680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9904999732971191,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9904000163078308,"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/computer-science","display_name":"Computer science","score":0.5728772282600403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728772282600403}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde60146.2024.00471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2186686397","https://openalex.org/W2997427139","https://openalex.org/W2997488476","https://openalex.org/W3025775630","https://openalex.org/W4367032190","https://openalex.org/W6758683703"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Data":[0],"lakes":[1,24],"are":[2,25],"becoming":[3],"increasingly":[4],"prevalent":[5],"for":[6,64,99,117,128],"big":[7],"data":[8,11,21,23,29,65,72,89,103,118,133,160],"management":[9],"and":[10,34,48,61,75,86,101,110,131,144,163],"analytics.":[12],"In":[13],"contrast":[14],"to":[15],"traditional":[16],"\u2018schema-on-write\u2019":[17],"approaches":[18,109],"such":[19],"as":[20],"warehouses,":[22],"repositories":[26],"storing":[27],"raw":[28],"in":[30,151],"its":[31],"original":[32],"formats":[33],"providing":[35],"a":[36,52,93,124],"common":[37],"access":[38],"interface.":[39],"Despite":[40],"the":[41,58,83,107,138,145,156],"strong":[42],"interest":[43],"raised":[44],"from":[45],"both":[46],"academia":[47],"industry,":[49],"there":[50],"is":[51,77],"large":[53],"body":[54],"of":[55,71,88,96,141,147,159],"ambiguity":[56],"regarding":[57],"definition,":[59],"functions":[60,116],"available":[62],"technologies":[63],"lakes.":[66,90,104,134],"A":[67],"complete,":[68],"coherent":[69],"picture":[70],"lake":[73,161],"challenges":[74,150],"solutions":[76,143],"still":[78],"missing.":[79],"This":[80],"survey":[81,123,153],"reviews":[82],"development,":[84],"architectures,":[85],"systems":[87,111],"We":[91,105,135],"provide":[92],"comprehensive":[94],"overview":[95],"research":[97,149,162],"questions":[98],"designing":[100],"building":[102],"classify":[106],"existing":[108,142],"based":[112],"on":[113],"their":[114],"provided":[115],"lakes,":[119],"which":[120],"makes":[121],"this":[122,152],"useful":[125],"technical":[126],"reference":[127],"designing,":[129],"implementing":[130],"deploying":[132],"hope":[136],"that":[137],"thorough":[139],"comparison":[140],"discussion":[146],"open":[148],"will":[154],"motivate":[155],"future":[157],"development":[158],"practice.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
