{"id":"https://openalex.org/W4312302709","doi":"https://doi.org/10.14778/3554821.3554857","title":"DPDS","display_name":"DPDS","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4312302709","doi":"https://doi.org/10.14778/3554821.3554857"},"language":"en","primary_location":{"id":"doi:10.14778/3554821.3554857","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3554821.3554857","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":true,"oa_status":"green","oa_url":"https://eprints.ncl.ac.uk/286704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013015057","display_name":"Adriane Chapman","orcid":"https://orcid.org/0000-0002-3814-2587"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Adriane Chapman","raw_affiliation_strings":["University of Southampton, UK"],"affiliations":[{"raw_affiliation_string":"University of Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007249357","display_name":"Luca Lauro","orcid":"https://orcid.org/0009-0003-0845-9596"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Lauro","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018918066","display_name":"Paolo Missier","orcid":"https://orcid.org/0000-0002-0978-2446"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["Newcastle University, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005845219","display_name":"Riccardo Torlone","orcid":"https://orcid.org/0000-0003-1484-3693"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Torlone","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013015057"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":2.5431,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92685484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"12","first_page":"3614","last_page":"3617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9868000149726868,"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"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9786999821662903,"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/computer-science","display_name":"Computer science","score":0.7491235733032227},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.7183314561843872},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6842522621154785},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.543753981590271},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.47424808144569397},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.462106317281723},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41833022236824036},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4105912446975708},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.40837031602859497},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.407114714384079},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37453576922416687},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.22859013080596924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18394169211387634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491235733032227},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.7183314561843872},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6842522621154785},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.543753981590271},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.47424808144569397},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.462106317281723},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41833022236824036},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4105912446975708},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40837031602859497},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.407114714384079},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37453576922416687},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.22859013080596924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18394169211387634},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/3554821.3554857","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3554821.3554857","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"},{"id":"pmh:oai:eprints.soton.ac.uk:477286","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:eprints.ncl.ac.uk:286704","is_oa":true,"landing_page_url":"https://eprints.ncl.ac.uk/286704","pdf_url":null,"source":{"id":"https://openalex.org/S4306402485","display_name":"Newcastle University ePrints (Newcastle Univesity)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I84884186","host_organization_name":"Newcastle University","host_organization_lineage":["https://openalex.org/I84884186"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:iris.uniroma3.it:11590/418208","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/418208","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:eprints.ncl.ac.uk:286704","is_oa":true,"landing_page_url":"https://eprints.ncl.ac.uk/286704","pdf_url":null,"source":{"id":"https://openalex.org/S4306402485","display_name":"Newcastle University ePrints (Newcastle Univesity)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I84884186","host_organization_name":"Newcastle University","host_organization_lineage":["https://openalex.org/I84884186"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1493590020","display_name":null,"funder_award_id":"EP/S028366/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2131850886","https://openalex.org/W2282821441","https://openalex.org/W2997591727","https://openalex.org/W3082494217","https://openalex.org/W3132433578"],"related_works":["https://openalex.org/W2742272031","https://openalex.org/W4385385304","https://openalex.org/W3086422166","https://openalex.org/W2151707824","https://openalex.org/W4245943305","https://openalex.org/W2053247611","https://openalex.org/W2295900847","https://openalex.org/W3024941504","https://openalex.org/W2465288476","https://openalex.org/W2590809092"],"abstract_inverted_index":{"Successful":[0],"data-driven":[1],"science":[2,74],"requires":[3],"a":[4,115,132],"complex":[5],"combination":[6],"of":[7,72,92,114,137,148,161],"data":[8,12,37,41,51,73,94,149,153],"engineering":[9],"pipelines":[10],"and":[11,16,35,46,66,129,140,144],"modelling":[13,42],"techniques.":[14],"Robust":[15],"defensible":[17],"results":[18],"can":[19,43],"only":[20],"be":[21,44],"achieved":[22],"when":[23],"each":[24,111,165],"step":[25],"in":[26,38,57,127],"the":[27,50,85,89,106,135,159,162],"pipeline":[28],"that":[29,101],"is":[30,60,102,125],"designed":[31,61],"to":[32,62,84,88,104,142,154],"clean,":[33],"transform":[34],"alter":[36],"preparation":[39],"for":[40],"justified,":[45],"its":[47],"effect":[48],"on":[49],"explained.":[52],"The":[53,121],"DPDS":[54,96],"toolkit":[55],"presented":[56],"this":[58],"paper":[59],"make":[63],"such":[64],"justification":[65],"explanation":[67],"process":[68],"an":[69,98],"integral":[70],"part":[71],"practice,":[75],"adding":[76],"value":[77],"while":[78],"remaining":[79],"as":[80,82],"un-intrusive":[81],"possible":[83],"analyst.":[86],"Catering":[87],"broad":[90],"community":[91],"python/pandas":[93],"engineers,":[95],"implements":[97],"observer":[99],"pattern":[100],"able":[103],"capture":[105],"fine-grained":[107],"provenance":[108,123],"associated":[109],"with":[110,134],"individual":[112],"element":[113],"dataframe,":[116],"across":[117],"multiple":[118],"transformation":[119],"steps.":[120],"resulting":[122],"graph":[124],"stored":[126],"Neo4j":[128],"queried":[130],"through":[131,164],"UI,":[133],"goal":[136],"helping":[138],"engineers":[139],"analysts":[141],"justify":[143],"explain":[145],"their":[146],"choice":[147],"operations,":[150],"from":[151],"raw":[152],"model":[155],"training,":[156],"by":[157],"highlighting":[158],"details":[160],"changes":[163],"transformation.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-01-04T00:00:00"}
