{"id":"https://openalex.org/W4411271387","doi":"https://doi.org/10.1109/msr66628.2025.00070","title":"Are the Majority of Public Computational Notebooks Pathologically Non-Executable?","display_name":"Are the Majority of Public Computational Notebooks Pathologically Non-Executable?","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4411271387","doi":"https://doi.org/10.1109/msr66628.2025.00070"},"language":"en","primary_location":{"id":"doi:10.1109/msr66628.2025.00070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr66628.2025.00070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 22nd International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100709067","display_name":"Tien Nguyen","orcid":"https://orcid.org/0000-0002-4016-9164"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tien Nguyen","raw_affiliation_strings":["Virginia Tech,Blacksburg,USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Blacksburg,USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007292608","display_name":"Waris Gill","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Waris Gill","raw_affiliation_strings":["Virginia Tech,Blacksburg,USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Blacksburg,USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003747461","display_name":"Muhammad Ali Gulzar","orcid":"https://orcid.org/0000-0002-8007-8662"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Gulzar","raw_affiliation_strings":["Virginia Tech,Blacksburg,USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Blacksburg,USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100709067"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":4.4085,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94502861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9908999800682068,"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":0.9908999800682068,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9739000201225281,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9678000211715698,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.867626428604126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6928756237030029},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.541952908039093}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.867626428604126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928756237030029},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.541952908039093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msr66628.2025.00070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr66628.2025.00070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 22nd International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2067436653","https://openalex.org/W2089745089","https://openalex.org/W2115010808","https://openalex.org/W2440056063","https://openalex.org/W2472803348","https://openalex.org/W2740279402","https://openalex.org/W2784241156","https://openalex.org/W2890114759","https://openalex.org/W2941232686","https://openalex.org/W2954370766","https://openalex.org/W2963723316","https://openalex.org/W2983901715","https://openalex.org/W3012094108","https://openalex.org/W3089843629","https://openalex.org/W3102273185","https://openalex.org/W3127102982","https://openalex.org/W3160344069","https://openalex.org/W3161042817","https://openalex.org/W3162449204","https://openalex.org/W3163379266","https://openalex.org/W4206329042","https://openalex.org/W4223432363","https://openalex.org/W4225469545","https://openalex.org/W4313006773","https://openalex.org/W4366587430","https://openalex.org/W4384918448","https://openalex.org/W4390739569","https://openalex.org/W4394653689","https://openalex.org/W4396831882","https://openalex.org/W4396833019","https://openalex.org/W4396833635","https://openalex.org/W4398234358","https://openalex.org/W4399251904","https://openalex.org/W4402531536","https://openalex.org/W4404783858","https://openalex.org/W4407278772","https://openalex.org/W6789715226","https://openalex.org/W6854866820","https://openalex.org/W6868843021","https://openalex.org/W6869432227","https://openalex.org/W6881206488"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2350278424","https://openalex.org/W2071432835","https://openalex.org/W4239401009","https://openalex.org/W82161441","https://openalex.org/W1576042299","https://openalex.org/W2181943964","https://openalex.org/W1528423264"],"abstract_inverted_index":{"Computational":[0],"notebooks":[1,46,74,87,134,141,153,181,251],"are":[2,47,98,200],"the":[3,57,110,218,223,237,273],"de":[4],"facto":[5],"platform":[6],"for":[7,125],"exploratory":[8],"data":[9,177],"science,":[10],"offering":[11],"an":[12],"interactive":[13,274],"programming":[14],"environment":[15],"where":[16,103],"users":[17],"can":[18,117,154],"create,":[19],"modify,":[20],"and":[21,67,75,91,100,121,138,142,148,231,240,265],"execute":[22],"code":[23,33,119],"cells":[24,160],"in":[25,85,152],"any":[26],"sequence.":[27],"However,":[28],"this":[29,129],"flexibility":[30],"often":[31],"introduces":[32],"quality":[34],"issues,":[35],"with":[36,182],"prior":[37,247],"studies":[38],"showing":[39],"that":[40,56,250,266],"approximately":[41],"$76":[42],"\\%$":[43,199,212],"of":[44,60,93,188,213,259],"public":[45,86,191],"non-executable,":[48],"raising":[49],"significant":[50],"concerns":[51],"about":[52],"reusability.":[53],"We":[54],"argue":[55],"traditional":[58,280],"notion":[59],"executability\u2014requiring":[61],"a":[62,123,168,186],"notebook":[63,275],"to":[64,173,178],"run":[65],"fully":[66,209],"without":[68,162],"error\u2014is":[69],"overly":[70],"rigid,":[71],"misclassifying":[72],"many":[73,258],"overestimating":[76],"their":[77,156,267],"non-executability.":[78],"This":[79],"paper":[80],"investigates":[81],"pathological":[82,139],"executability":[83,116,157,225,254,268,282],"issues":[84,151],"under":[88],"varying":[89],"notions":[90],"degrees":[92],"executability.":[94],"Notebooks,":[95],"by":[96,226,235],"construction,":[97],"incrementally":[99],"interactively":[101],"executed,":[102],"each":[104],"cell":[105],"execution":[106,150],"advances":[107],"logic":[108],"toward":[109],"notebook\u2019s":[111],"goal.":[112],"Even":[113],"partially":[114,219],"improving":[115],"improve":[118,155],"comprehension":[120],"offer":[122,261],"pathway":[124],"dynamic":[126],"analyses.":[127],"With":[128],"insight,":[130],"we":[131,166],"first":[132],"categorize":[133],"into":[135],"potentially":[136],"restorable":[137,205],"non-executable":[140,180,195],"then":[143],"measure":[144],"how":[145],"removing":[146],"misconfiguration":[147],"superficial":[149],"(i.e.,":[158],"additional":[159],"executed":[161],"error).":[163],"For":[164,204],"instance,":[165],"use":[167],"Large":[169],"Language":[170],"Model":[171],"(LLM)":[172],"generate":[174],"synthetic":[175,242],"input":[176],"restore":[179,210],"\u201cFileNotFound\u201d":[183],"errors.":[184],"In":[185],"dataset":[187],"42,546":[189],"popular":[190],"notebooks,":[192,196,206],"containing":[193],"34,659":[194],"only":[197],"$21.3":[198],"truly":[201],"pathologically":[202],"non-executable.":[203],"LLM-based":[207],"methods":[208],"$5.4":[211],"previously":[214,256],"nonexecutable":[215],"notebooks.":[216],"Among":[217],"restored,":[220],"it":[221],"improves":[222],"notebooks\u2019":[224],"$\\mathbf{4":[227],"0.":[228],"5":[229],"\\%}$":[230,234],"$\\mathbf{2":[232],"8":[233],"installing":[236],"correct":[238],"modules":[239],"generating":[241],"data.":[243],"These":[244],"findings":[245],"challenge":[246],"assumptions,":[248],"suggesting":[249],"have":[252],"higher":[253],"than":[255,278],"reported,":[257],"which":[260],"valuable":[262],"partial":[263],"execution,":[264],"should":[269],"be":[270],"evaluated":[271],"within":[272],"paradigm":[276],"rather":[277],"through":[279],"software":[281],"standards.":[283]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}