{"id":"https://openalex.org/W4414244639","doi":"https://doi.org/10.14778/3750601.3750694","title":"Data Discovery in Data Lakes: Operations, Indexes, Systems","display_name":"Data Discovery in Data Lakes: Operations, Indexes, Systems","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414244639","doi":"https://doi.org/10.14778/3750601.3750694"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750694","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/A5009128577","display_name":"Ziawasch Abedjan","orcid":"https://orcid.org/0000-0002-2846-1373"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ziawasch Abedjan","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039065595","display_name":"Mahdi Esmailoghli","orcid":"https://orcid.org/0009-0009-2148-6402"},"institutions":[{"id":"https://openalex.org/I4210115355","display_name":"Institut f\u00fcr Hygiene und Umwelt","ror":"https://ror.org/029djbz77","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210115355","https://openalex.org/I4210133928"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mahdi Esmailoghli","raw_affiliation_strings":["HU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"HU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210115355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009128577"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30610847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"12","first_page":"5455","last_page":"5459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"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":0.9987000226974487,"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":0.998199999332428,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-discovery","display_name":"Data discovery","score":0.6502000093460083},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6337000131607056},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6031000018119812},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5449000000953674},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3939000070095062},{"id":"https://openalex.org/keywords/service-discovery","display_name":"Service discovery","score":0.3849000036716461},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.6502000093460083},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C144097018","wikidata":"https://www.wikidata.org/wiki/Q4329404","display_name":"Service discovery","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38190001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.3059000074863434},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750694","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1969621019","https://openalex.org/W1996505782","https://openalex.org/W2065259291","https://openalex.org/W2083619093","https://openalex.org/W2105436061","https://openalex.org/W2120908895","https://openalex.org/W2427822648","https://openalex.org/W2469798230","https://openalex.org/W2509030362","https://openalex.org/W2560674852","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2948163032","https://openalex.org/W2950817225","https://openalex.org/W2963174348","https://openalex.org/W2964133178","https://openalex.org/W2970059736","https://openalex.org/W3014616325","https://openalex.org/W3031051334","https://openalex.org/W3032215537","https://openalex.org/W3139909695","https://openalex.org/W3164968002","https://openalex.org/W3196867679","https://openalex.org/W3209203378","https://openalex.org/W4210558765","https://openalex.org/W4283383705","https://openalex.org/W4285335450","https://openalex.org/W4289533971","https://openalex.org/W4375928372","https://openalex.org/W4413361314","https://openalex.org/W6912751010","https://openalex.org/W6966973472"],"related_works":[],"abstract_inverted_index":{"Data":[0],"discovery":[1,13,18,29,62,65],"has":[2],"gained":[3],"significant":[4],"traction":[5],"in":[6,11,66],"the":[7,23],"database":[8],"community":[9],"resulting":[10],"various":[12],"operations,":[14,40],"index":[15],"schemes,":[16],"and":[17,25,35,44,64],"systems.":[19],"This":[20],"tutorial":[21],"explores":[22],"architecture":[24],"components":[26],"of":[27],"data":[28,61],"systems,":[30,60],"focusing":[31],"on":[32],"indexing":[33],"structures":[34],"scalable":[36],"algorithms":[37],"for":[38,58],"typical":[39],"such":[41],"as":[42],"join":[43],"union":[45],"discovery.":[46],"While":[47],"giving":[48],"insights":[49],"into":[50],"individual":[51],"algorithms,":[52],"we":[53],"point":[54],"out":[55],"open":[56],"challenges":[57],"holistic":[59],"evaluation,":[63],"federated":[67],"setups.":[68]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}