{"id":"https://openalex.org/W4309647888","doi":"https://doi.org/10.1145/3564695.3564773","title":"Revisiting data lakes","display_name":"Revisiting data lakes","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4309647888","doi":"https://doi.org/10.1145/3564695.3564773"},"language":"en","primary_location":{"id":"doi:10.1145/3564695.3564773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3564695.3564773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Middleware Conference Industrial Track","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/A5041465821","display_name":"Daniel Bauer","orcid":"https://orcid.org/0000-0002-0420-9800"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Bauer","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053063022","display_name":"Chris Giblin","orcid":"https://orcid.org/0000-0003-1871-3693"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Giblin","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086006027","display_name":"Luis Garc\u00e9s-Erice","orcid":"https://orcid.org/0000-0002-6785-5631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luis Garc\u00e9s-Erice","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041510007","display_name":"Niels Pardon","orcid":"https://orcid.org/0000-0001-7659-5280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niels Pardon","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038726171","display_name":"Se\u00e1n Rooney","orcid":"https://orcid.org/0009-0003-9861-5918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sean Rooney","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019170427","display_name":"Enrico Toniato","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enrico Toniato","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041348121","display_name":"Peter Urbanetz","orcid":"https://orcid.org/0000-0001-5357-2318"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter Urbanetz","raw_affiliation_strings":["IBM Research Europe, R\u00fcschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research Europe, R\u00fcschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041465821"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62685966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988999962806702,"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/metadata","display_name":"Metadata","score":0.96593177318573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114917278289795},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.5569968819618225},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5307673811912537},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.5078657269477844},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.4414345622062683},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.4296637773513794},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41179099678993225},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3920704126358032},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32036682963371277},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10237205028533936}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.96593177318573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114917278289795},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.5569968819618225},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5307673811912537},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.5078657269477844},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.4414345622062683},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.4296637773513794},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41179099678993225},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3920704126358032},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32036682963371277},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10237205028533936}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3564695.3564773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3564695.3564773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Middleware Conference Industrial Track","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2033523472","https://openalex.org/W2110086534","https://openalex.org/W2142825844","https://openalex.org/W2612261081","https://openalex.org/W2668736619","https://openalex.org/W3111009181","https://openalex.org/W3163828919","https://openalex.org/W4206380908"],"related_works":["https://openalex.org/W3084772717","https://openalex.org/W2907247951","https://openalex.org/W2380261968","https://openalex.org/W2376038160","https://openalex.org/W3199469221","https://openalex.org/W1512114296","https://openalex.org/W2374379029","https://openalex.org/W2018424284","https://openalex.org/W2390798650","https://openalex.org/W2885275449"],"abstract_inverted_index":{"We":[0,21,32,51],"argue":[1],"that":[2,25,38],"emerging":[3],"federated":[4],"data":[5],"management":[6],"architectures":[7],"require":[8],"a":[9,19,29,44],"means":[10],"of":[11],"gathering,":[12],"linking,":[13],"curating":[14],"and":[15,46,64],"enriching":[16],"metadata":[17,30,55],"in":[18],"graph.":[20],"call":[22],"the":[23,34],"system":[24,45],"supports":[26],"these":[27],"tasks":[28],"lake.":[31],"explain":[33],"underlying":[35],"architectural":[36],"principles":[37],"are":[39],"required":[40],"to":[41,59],"achieve":[42,60],"such":[43],"describe":[47],"our":[48,54],"current":[49],"implementation.":[50],"show":[52],"how":[53],"lake":[56],"is":[57],"used":[58],"certain":[61],"advanced":[62],"capabilities":[63],"report":[65],"on":[66],"its":[67],"performance.":[68]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}