{"id":"https://openalex.org/W4415332639","doi":"https://doi.org/10.1145/3736731.3746159","title":"Similarity-Based Assessment of Computational Reproducibility in Jupyter Notebooks","display_name":"Similarity-Based Assessment of Computational Reproducibility in Jupyter Notebooks","publication_year":2025,"publication_date":"2025-07-29","ids":{"openalex":"https://openalex.org/W4415332639","doi":"https://doi.org/10.1145/3736731.3746159"},"language":"en","primary_location":{"id":"doi:10.1145/3736731.3746159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736731.3746159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM Conference on Reproducibility and Replicability","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.23645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110496794","display_name":"Arfat Hossain","orcid":"https://orcid.org/0009-0008-3229-8821"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A S M Shahadat Hossain","raw_affiliation_strings":["University of Missouri, Columbia, Missouri, USA"],"raw_orcid":"https://orcid.org/0009-0008-3229-8821","affiliations":[{"raw_affiliation_string":"University of Missouri, Columbia, Missouri, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Colin Brown","orcid":"https://orcid.org/0000-0002-2214-2726"},"institutions":[{"id":"https://openalex.org/I102502594","display_name":"Northern Illinois University","ror":"https://ror.org/012wxa772","country_code":"US","type":"education","lineage":["https://openalex.org/I102502594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Brown","raw_affiliation_strings":["Northern Illinois University, DeKalb, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-2214-2726","affiliations":[{"raw_affiliation_string":"Northern Illinois University, DeKalb, Illinois, USA","institution_ids":["https://openalex.org/I102502594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109832145","display_name":"David Koop","orcid":"https://orcid.org/0000-0002-4422-6162"},"institutions":[{"id":"https://openalex.org/I102502594","display_name":"Northern Illinois University","ror":"https://ror.org/012wxa772","country_code":"US","type":"education","lineage":["https://openalex.org/I102502594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Koop","raw_affiliation_strings":["Northern Illinois University, DeKalb, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-4422-6162","affiliations":[{"raw_affiliation_string":"Northern Illinois University, DeKalb, Illinois, USA","institution_ids":["https://openalex.org/I102502594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071436717","display_name":"Tanu Malik","orcid":"https://orcid.org/0009-0007-9656-727X"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanu Malik","raw_affiliation_strings":["University of Missouri, Columbia, Missouri, USA"],"raw_orcid":"https://orcid.org/0009-0007-9656-727X","affiliations":[{"raw_affiliation_string":"University of Missouri, Columbia, Missouri, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110496794"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27666182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9929999709129333,"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":0.9929999709129333,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9767000079154968,"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/python","display_name":"Python (programming language)","score":0.8252000212669373},{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.6729999780654907},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3962000012397766},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3792000114917755}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8252000212669373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718500018119812},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.6729999780654907},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3736731.3746159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736731.3746159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM Conference on Reproducibility and Replicability","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.23645","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.23645","pdf_url":"https://arxiv.org/pdf/2509.23645","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.23645","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.23645","pdf_url":"https://arxiv.org/pdf/2509.23645","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1973207880","https://openalex.org/W2015159529","https://openalex.org/W2112796928","https://openalex.org/W2133665775","https://openalex.org/W2784241156","https://openalex.org/W2900341572","https://openalex.org/W2944196828","https://openalex.org/W2954370766","https://openalex.org/W3035965352","https://openalex.org/W3081184337","https://openalex.org/W3092022376","https://openalex.org/W3099878876","https://openalex.org/W3117364138","https://openalex.org/W3121485564","https://openalex.org/W3149892364","https://openalex.org/W3150635270","https://openalex.org/W3160344069","https://openalex.org/W3161776805","https://openalex.org/W3161971890","https://openalex.org/W3184613644","https://openalex.org/W3201128376","https://openalex.org/W3210652723","https://openalex.org/W4225576441","https://openalex.org/W4240052332","https://openalex.org/W4242395378","https://openalex.org/W4295905006","https://openalex.org/W4296023017","https://openalex.org/W4312521811","https://openalex.org/W4313033767","https://openalex.org/W4390104160","https://openalex.org/W4390739569","https://openalex.org/W6969259846"],"related_works":[],"abstract_inverted_index":{"Computational":[0],"reproducibility":[1,71],"refers":[2],"to":[3,41,87,93,126,143,157],"obtaining":[4],"consistent":[5],"results":[6,39,73],"when":[7],"rerunning":[8,30],"an":[9,104],"experiment.":[10],"Jupyter":[11,32,75,147],"Notebook,":[12],"a":[13,31,66,107,112,133,144],"web-based":[14],"computational":[15,23,55,159],"notebook":[16],"application,":[17],"facilitates":[18],"running,":[19],"publishing,":[20],"and":[21],"sharing":[22],"experiments":[24],"along":[25],"with":[26],"their":[27],"results.":[28],"However,":[29],"Notebook":[33],"may":[34],"not":[35],"always":[36],"generate":[37],"identical":[38],"due":[40],"various":[42,151],"factors,":[43],"such":[44],"as":[45,120,122],"randomness,":[46],"changes":[47],"in":[48,53,74,106,115,136],"library":[49],"versions,":[50],"or":[51],"variations":[52],"the":[54,60,70,116,138],"environment.":[56],"This":[57],"paper":[58,130],"introduces":[59],"Similarity-based":[61],"Reproducibility":[62],"Index":[63],"(SRI)":[64],"--":[65],"metric":[67,140],"for":[68],"assessing":[69],"of":[72,90,146],"Notebooks.":[76],"SRI":[77,110],"employs":[78],"novel":[79],"methods":[80],"developed":[81],"based":[82],"on":[83],"similarity":[84,152],"metrics":[85,153],"specific":[86],"different":[88],"types":[89],"Python":[91],"objects":[92],"compare":[94],"rerun":[95,108],"outputs":[96],"against":[97],"original":[98],"outputs.":[99],"For":[100],"every":[101],"cell":[102],"generating":[103],"output":[105],"notebook,":[109],"reports":[111],"quantitative":[113],"score":[114],"range":[117],"[0,":[118],"1]":[119],"well":[121],"some":[123],"qualitative":[124],"insights":[125],"assess":[127],"reproducibility.":[128,160],"The":[129],"also":[131],"includes":[132],"case":[134],"study":[135],"which":[137],"proposed":[139],"is":[141],"applied":[142],"set":[145],"Notebooks,":[148],"demonstrating":[149],"how":[150],"can":[154],"be":[155],"leveraged":[156],"quantify":[158]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-19T00:00:00"}