{"id":"https://openalex.org/W6906486741","doi":"https://doi.org/10.18420/se2025-07","title":"Analyzing the reproducibility of research-related Jupyter notebooks at scale","display_name":"Analyzing the reproducibility of research-related Jupyter notebooks at scale","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6906486741","doi":"https://doi.org/10.18420/se2025-07"},"language":"en","primary_location":{"id":"doi:10.18420/se2025-07","is_oa":true,"landing_page_url":"https://doi.org/10.18420/se2025-07","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210134436","host_organization_name":"German Informatics Society","host_organization_lineage":["https://openalex.org/I4210134436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/se2025-07","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mietchen, Daniel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mietchen, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Samuel, Sheeba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel, Sheeba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25588247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8442999720573425,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8442999720573425,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.10920000076293945,"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/T11937","display_name":"Research Data Management Practices","score":0.012500000186264515,"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/reproducibility","display_name":"Reproducibility","score":0.7910000085830688},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6625999808311462},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49000000953674316},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.4196000099182129}],"concepts":[{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4876999855041504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4537000060081482},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.4196000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/se2025-07","is_oa":true,"landing_page_url":"https://doi.org/10.18420/se2025-07","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210134436","host_organization_name":"German Informatics Society","host_organization_lineage":["https://openalex.org/I4210134436"],"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-journal"}],"best_oa_location":{"id":"doi:10.18420/se2025-07","is_oa":true,"landing_page_url":"https://doi.org/10.18420/se2025-07","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210134436","host_organization_name":"German Informatics Society","host_organization_lineage":["https://openalex.org/I4210134436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,35,66,133],"address":[1],"computational":[2,19],"reproducibility":[3,20,77,91],"of":[4,21,95,109,116,151],"publication-associated":[5],"Jupyter":[6,22,117],"notebooks":[7,23,38,83,118,152],"at":[8],"3":[9],"levels:":[10],"(i)":[11],"using":[12,97],"fully":[13],"automated":[14],"workflows,":[15],"we":[16,169],"analyzed":[17],"the":[18,29,41,62,82,99,107,114,135],"associated":[24,186],"with":[25,141,187],"publications":[26],"indexed":[27,121],"in":[28,56,93,122,127,155,171],"biomedical":[30,188],"literature":[31],"repository":[32],"PubMed":[33,104,123],"Central.":[34],"identified":[36],"such":[37],"by":[39,158,160,163],"mining":[40],"article\u2019s":[42],"full":[43],"text,":[44],"trying":[45],"to":[46,53,61,81,183],"locate":[47],"them":[48,55],"on":[49,103,172],"GitHub,":[50],"and":[51,70,72,78,94,175,179],"attempting":[52],"rerun":[54],"an":[57],"environment":[58],"as":[59,64],"close":[60],"original":[63],"possible.":[65],"documented":[67],"reproduction":[68],"success":[69],"exceptions":[71],"explored":[73],"relationships":[74],"between":[75],"notebook":[76],"variables":[79],"related":[80],"or":[84,154,162],"publications.":[85,189],"(ii)":[86],"This":[87],"study":[88],"represents":[89],"a":[90,128,138,142],"attempt":[92],"itself,":[96],"essentially":[98],"same":[100],"methodology":[101],"twice":[102],"Central":[105,124],"over":[106],"course":[108],"2":[110],"years,":[111],"during":[112],"which":[113],"corpus":[115,136],"from":[119],"articles":[120],"has":[125],"grown":[126],"highly":[129],"dynamic":[130],"fashion.":[131],"(iii)":[132],"imported":[134],"into":[137],"knowledge":[139],"graph":[140],"public":[143],"SPARQL":[144],"endpoint":[145],"that":[146],"allows":[147],"for":[148],"fine-grained":[149],"exploration":[150],"individually":[153],"aggregation":[156],"(e.g.":[157],"topic,":[159],"journal":[161],"error":[164],"type).":[165],"In":[166],"this":[167],"talk,":[168],"zoom":[170],"common":[173],"problems":[174],"practices,":[176],"highlight":[177],"trends,":[178],"discuss":[180],"potential":[181],"improvements":[182],"Jupyter-related":[184],"workflows":[185]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}