{"id":"https://openalex.org/W3029302266","doi":"https://doi.org/10.1109/vl/hcc50065.2020.9127202","title":"Code Duplication and Reuse in Jupyter Notebooks","display_name":"Code Duplication and Reuse in Jupyter Notebooks","publication_year":2020,"publication_date":"2020-07-16","ids":{"openalex":"https://openalex.org/W3029302266","doi":"https://doi.org/10.1109/vl/hcc50065.2020.9127202","mag":"3029302266"},"language":"en","primary_location":{"id":"doi:10.1109/vl/hcc50065.2020.9127202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vl/hcc50065.2020.9127202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.13709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053600655","display_name":"Andreas P. Koenzen","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Andreas P. Koenzen","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Victoria, Canada","University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033114444","display_name":"Neil Ernst","orcid":"https://orcid.org/0000-0001-5992-2366"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Neil A. Ernst","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Victoria, Canada","University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038905934","display_name":"Margaret\u2010Anne Storey","orcid":"https://orcid.org/0000-0003-2278-2536"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Margaret-Anne D. Storey","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Victoria, Canada","University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053600655"],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":0.2783,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63932305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9983000159263611,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9922000169754028,"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/reuse","display_name":"Reuse","score":0.8112667798995972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7033089399337769},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6987457871437073},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.6887922883033752},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4771137535572052},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4469241797924042},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4380742013454437},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4173825681209564},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.39399099349975586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13279610872268677}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8112667798995972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033089399337769},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6987457871437073},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.6887922883033752},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4771137535572052},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4469241797924042},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4380742013454437},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4173825681209564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39399099349975586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13279610872268677},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/vl/hcc50065.2020.9127202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vl/hcc50065.2020.9127202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.13709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.13709","pdf_url":"https://arxiv.org/pdf/2005.13709","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3029302266","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.13709.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.library.uvic.ca:1828/12137","is_oa":false,"landing_page_url":"http://hdl.handle.net/1828/12137","pdf_url":null,"source":{"id":"https://openalex.org/S4306401509","display_name":"UVic\u2019s Research and Learning Repository (University of Victoria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I212119943","host_organization_name":"University of Victoria","host_organization_lineage":["https://openalex.org/I212119943"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:zenodo.org:3836691","is_oa":true,"landing_page_url":"https://zenodo.org/record/3836691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2005.13709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.13709","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.3836690","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3836690","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.3836691","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3836691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.13709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.13709","pdf_url":"https://arxiv.org/pdf/2005.13709","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3029302266.pdf","grobid_xml":"https://content.openalex.org/works/W3029302266.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1857184435","https://openalex.org/W2013638584","https://openalex.org/W2044102377","https://openalex.org/W2090432523","https://openalex.org/W2115570304","https://openalex.org/W2119887272","https://openalex.org/W2122401044","https://openalex.org/W2125083169","https://openalex.org/W2128888088","https://openalex.org/W2141271901","https://openalex.org/W2145544369","https://openalex.org/W2153887189","https://openalex.org/W2171955640","https://openalex.org/W2298313545","https://openalex.org/W2610517421","https://openalex.org/W2622688141","https://openalex.org/W2768736423","https://openalex.org/W2770408320","https://openalex.org/W2784241156","https://openalex.org/W2796040126","https://openalex.org/W2820738241","https://openalex.org/W2898253813","https://openalex.org/W2898377472","https://openalex.org/W2898671507","https://openalex.org/W2941232686","https://openalex.org/W2952755643","https://openalex.org/W2964148489","https://openalex.org/W3012094108","https://openalex.org/W3100811706","https://openalex.org/W3104103145","https://openalex.org/W6636915900","https://openalex.org/W6638928880","https://openalex.org/W6697318023","https://openalex.org/W6739051727","https://openalex.org/W6752748919","https://openalex.org/W6764932524","https://openalex.org/W6765015735"],"related_works":["https://openalex.org/W3043652335","https://openalex.org/W2941232686","https://openalex.org/W933475039","https://openalex.org/W3091454237","https://openalex.org/W2462776371","https://openalex.org/W2810627707","https://openalex.org/W2971660263","https://openalex.org/W2106146658","https://openalex.org/W2891332953","https://openalex.org/W1954856259","https://openalex.org/W2052988310","https://openalex.org/W3037760072","https://openalex.org/W2006291142","https://openalex.org/W3137174954","https://openalex.org/W2309459597","https://openalex.org/W2610517421","https://openalex.org/W2492006053","https://openalex.org/W3113274029","https://openalex.org/W2032514319","https://openalex.org/W2739878306"],"abstract_inverted_index":{"Duplicating":[0],"one's":[1],"own":[2,146],"code":[3,43,54,97,113,151],"makes":[4],"it":[5],"faster":[6],"to":[7,24,53,149],"write":[8],"software.":[9],"This":[10],"expediency":[11],"is":[12],"particularly":[13],"valuable":[14],"for":[15,67,96],"users":[16,23],"of":[17,61,112,135],"computational":[18,47,62],"notebooks.":[19,121],"Duplication":[20],"allows":[21],"notebook":[22],"quickly":[25],"test":[26],"hypotheses":[27],"and":[28,40,49,69,105],"iterate":[29],"over":[30],"data.":[31],"In":[32],"this":[33,89],"paper,":[34],"we":[35,91],"explore":[36],"how":[37,39,75],"much,":[38],"from":[41,152],"where":[42,115],"duplication":[44,70],"occurs":[45,78],"in":[46,58,100,127,138],"notebooks,":[48,104],"identify":[50],"potential":[51],"barriers":[52,81],"reuse.":[55],"Previous":[56],"work":[57],"the":[59],"area":[60],"notebooks":[63],"describes":[64],"developers'":[65],"motivations":[66],"reuse":[68,77,150],"but":[71],"does":[72],"not":[73],"show":[74],"much":[76],"or":[79],"which":[80],"they":[82],"face":[83],"when":[84],"reusing":[85],"code.":[86],"To":[87],"address":[88],"gap,":[90],"first":[92],"analyzed":[93],"GitHub":[94],"repositories":[95,126],"duplicates":[98],"contained":[99],"a":[101,131],"repository's":[102],"Jupyter":[103],"then":[106],"conducted":[107],"an":[108],"observational":[109],"user":[110,140],"study":[111],"reuse,":[114],"participants":[116,143],"solved":[117],"specific":[118],"tasks":[119],"using":[120],"Our":[122],"findings":[123],"reveal":[124],"that":[125],"our":[128,139],"sample":[129],"have":[130],"mean":[132],"self-duplication":[133],"rate":[134],"7.6%.":[136],"However,":[137],"study,":[141],"few":[142],"duplicated":[144],"their":[145],"code,":[147],"preferring":[148],"online":[153],"sources.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}