{"id":"https://openalex.org/W2232417456","doi":"https://doi.org/10.14778/2824032.2824086","title":"Data profiling with metanome","display_name":"Data profiling with metanome","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2232417456","doi":"https://doi.org/10.14778/2824032.2824086","mag":"2232417456"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824086","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824086","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/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028075850","display_name":"Tanja Bergmann","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Bergmann","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017099048","display_name":"Moritz Finke","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Finke","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081248497","display_name":"Jakob Zwiener","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Zwiener","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047144042"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":13.1695,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.98834467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"12","first_page":"1860","last_page":"1863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9959999918937683,"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/profiling","display_name":"Profiling (computer programming)","score":0.8460474014282227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77308589220047},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7290117740631104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4660075306892395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3745509684085846},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32700201869010925},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1622227430343628},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08632045984268188}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8460474014282227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77308589220047},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7290117740631104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4660075306892395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3745509684085846},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32700201869010925},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1622227430343628},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08632045984268188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824086","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824086","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":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1502954553","https://openalex.org/W1537955876","https://openalex.org/W1571341547","https://openalex.org/W1881756506","https://openalex.org/W2024443169","https://openalex.org/W2116790080","https://openalex.org/W2159186077","https://openalex.org/W2159328231","https://openalex.org/W2166549982","https://openalex.org/W2182148130","https://openalex.org/W2241277057","https://openalex.org/W2266772167"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W599624254"],"abstract_inverted_index":{"Data":[0],"profiling":[1,35,58,92,98,107,128,152],"is":[2,102,124,148],"the":[3,31,116],"discipline":[4],"of":[5,17,33,74,119],"discovering":[6],"metadata":[7,12,165],"about":[8],"given":[9],"datasets.":[10],"The":[11],"itself":[13],"serve":[14],"a":[15],"variety":[16],"use":[18],"cases,":[19],"such":[20,77],"as":[21,78],"data":[22,24,34,44],"integration,":[23],"cleansing,":[25],"or":[26,84],"query":[27],"optimization.":[28],"Due":[29],"to":[30,63,104,125,136,150,155,159],"importance":[32],"in":[36,49,109,139],"practice,":[37],"many":[38,96],"tools":[39,53],"have":[40],"emerged":[41],"that":[42,60,94],"support":[43,56,137],"scientists":[45],"and":[46,71,135,141,158],"IT":[47],"professionals":[48],"this":[50],"task.":[51],"These":[52],"provide":[54,126],"good":[55],"for":[57],"statistics":[59,108],"are":[61,67],"easy":[62],"compute,":[64],"but":[65],"they":[66],"usually":[68],"lacking":[69],"automatic":[70,117],"efficient":[72],"discovery":[73,118],"complex":[75,120],"statistics,":[76],"inclusion":[79],"dependencies,":[80],"unique":[81],"column":[82],"combinations,":[83],"functional":[85],"dependencies.":[86],"We":[87],"present":[88],"Metanome,":[89],"an":[90],"extensible":[91],"platform":[93],"incorporates":[95],"state-of-the-art":[97],"algorithms.":[99,144],"While":[100],"Metanome":[101,147],"able":[103,149],"calculate":[105],"simple":[106],"relational":[110],"data,":[111],"its":[112],"focus":[113],"lies":[114],"on":[115],"metadata.":[121],"Metanome's":[122],"goal":[123],"novel":[127],"algorithms":[129],"from":[130],"research,":[131],"perform":[132],"comparative":[133],"evaluations,":[134],"developers":[138],"building":[140],"testing":[142],"new":[143],"In":[145],"addition,":[146],"rank":[151],"results":[153],"according":[154],"various":[156],"metrics":[157],"visualize":[160],"the,":[161],"at":[162],"times,":[163],"large":[164],"sets.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
