{"id":"https://openalex.org/W2891222064","doi":"https://doi.org/10.1145/3241403.3241437","title":"Data wrangling at scale","display_name":"Data wrangling at scale","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2891222064","doi":"https://doi.org/10.1145/3241403.3241437","mag":"2891222064"},"language":"en","primary_location":{"id":"doi:10.1145/3241403.3241437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3241403.3241437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th European Conference on Software Architecture: Companion Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10281/219493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064116719","display_name":"Nikolay Nikolov","orcid":"https://orcid.org/0000-0003-3266-0751"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Nikolay Nikolov","raw_affiliation_strings":["SINTEF, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SINTEF, Oslo, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079768184","display_name":"Michele Ciavotta","orcid":"https://orcid.org/0000-0002-2480-966X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Ciavotta","raw_affiliation_strings":["University of Milan-Bicocca, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049354209","display_name":"Flavio De Paoli","orcid":"https://orcid.org/0000-0002-5047-7371"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio De Paoli","raw_affiliation_strings":["University of Milan-Bicocca, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9937000274658203,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527239918708801},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5984492301940918},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5838803052902222},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5588720440864563},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47358566522598267},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4631369113922119},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.4380054473876953},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4090040922164917},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.3504756689071655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30030134320259094},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.1917608380317688},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15786412358283997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1427323818206787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527239918708801},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5984492301940918},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5838803052902222},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5588720440864563},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47358566522598267},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4631369113922119},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.4380054473876953},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4090040922164917},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3504756689071655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30030134320259094},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.1917608380317688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15786412358283997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1427323818206787},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3241403.3241437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3241403.3241437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th European Conference on Software Architecture: Companion Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/219493","is_oa":true,"landing_page_url":"http://hdl.handle.net/10281/219493","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:boa.unimib.it:10281/219493","is_oa":true,"landing_page_url":"http://hdl.handle.net/10281/219493","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W2295276225","https://openalex.org/W2493970676","https://openalex.org/W2518514431","https://openalex.org/W2560528144","https://openalex.org/W2776558668","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W2369244966","https://openalex.org/W2386066260","https://openalex.org/W1492261612","https://openalex.org/W2374519217","https://openalex.org/W2012941781","https://openalex.org/W2159704347","https://openalex.org/W2156949561","https://openalex.org/W2393271921","https://openalex.org/W2089133691","https://openalex.org/W2586460527"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,6,46,86],"subsystem":[4],"of":[5,16,37,49,67,89,95],"comprehensive":[7],"platform":[8,59],"dedicated":[9],"to":[10,32],"data":[11,18,69,93],"transformation,":[12],"linking":[13],"and":[14,23,35,40,53,63],"extension":[15],"large":[17],"sets.":[19],"Furthermore,":[20],"we":[21],"detail":[22],"discuss":[24],"both":[25,61],"the":[26,33,38,41,50,58,68,76],"main":[27],"requirements":[28],"that":[29],"have":[30,81],"led":[31],"design":[34,62],"development":[36],"platform,":[39],"devised":[42],"approach,":[43],"which":[44,72],"is":[45,73],"direct":[47],"outcome":[48],"requirement":[51],"elicitation":[52],"discussion":[54],"phase.":[55],"In":[56],"particular,":[57],"supports":[60],"run":[64],"time":[65],"aspects":[66],"transformation":[70],"process,":[71],"reflected":[74],"in":[75],"architecture.":[77],"Some":[78],"initial":[79],"tests":[80],"been":[82],"carried":[83],"out":[84],"on":[85,92],"prototype":[87],"implementation":[88],"our":[90],"architecture":[91],"sets":[94],"~1TB":[96],"featuring":[97],"promising":[98],"performance.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-09-27T00:00:00"}
