{"id":"https://openalex.org/W4283066665","doi":"https://doi.org/10.1109/icse-seip55303.2022.9794067","title":"A Static Analysis Framework for Data Science Notebooks","display_name":"A Static Analysis Framework for Data Science Notebooks","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W4283066665","doi":"https://doi.org/10.1109/icse-seip55303.2022.9794067"},"language":"en","primary_location":{"id":"doi:10.1109/icse-seip55303.2022.9794067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icse-seip55303.2022.9794067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","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/A5009881146","display_name":"Pavle Suboti\u0107","orcid":"https://orcid.org/0000-0002-6536-3932"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Pavle Subotic","raw_affiliation_strings":["Microsoft,Serbia","Microsoft, Serbia"],"affiliations":[{"raw_affiliation_string":"Microsoft,Serbia","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Serbia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043415467","display_name":"Lazar Miliki\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lazar Milikic","raw_affiliation_strings":["Microsoft,Serbia","Microsoft, Serbia"],"affiliations":[{"raw_affiliation_string":"Microsoft,Serbia","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Serbia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046825007","display_name":"Milan Stoji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Milan Stojic","raw_affiliation_strings":["Microsoft,Serbia","Microsoft, Serbia"],"affiliations":[{"raw_affiliation_string":"Microsoft,Serbia","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Serbia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009881146"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.4252,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90766848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9973000288009644,"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":0.9973000288009644,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388243913650513},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8146160244941711},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6757220029830933},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5903784036636353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5897715091705322},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5789459943771362},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5142342448234558},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5092333555221558},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4542423486709595},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.43386411666870117},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.4138088524341583},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3302368223667145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388243913650513},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8146160244941711},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6757220029830933},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5903784036636353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5897715091705322},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5789459943771362},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5142342448234558},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5092333555221558},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4542423486709595},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.43386411666870117},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4138088524341583},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3302368223667145},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icse-seip55303.2022.9794067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icse-seip55303.2022.9794067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W563453116","https://openalex.org/W1503248989","https://openalex.org/W2014764321","https://openalex.org/W2043100293","https://openalex.org/W2046213250","https://openalex.org/W2095686702","https://openalex.org/W2978700448","https://openalex.org/W3045754299","https://openalex.org/W3089684372","https://openalex.org/W3089843629","https://openalex.org/W3105684693","https://openalex.org/W3125702975","https://openalex.org/W3141903600","https://openalex.org/W6787206740"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W2352266335","https://openalex.org/W2375074373"],"abstract_inverted_index":{"Notebooks":[0],"provide":[1],"an":[2],"interactive":[3,141],"environment":[4],"for":[5,91],"programmers":[6],"to":[7],"develop":[8],"code,":[9],"analyse":[10],"data":[11,27,45],"and":[12,55,107],"inject":[13],"interleaved":[14],"visualisations":[15],"in":[16,79,129],"a":[17,23,43,62,85,102,132],"single":[18],"environment.":[19],"Despite":[20],"their":[21,71],"flexibility,":[22],"major":[24],"pitfall":[25],"that":[26,64,82,119],"scientists":[28,46],"encounter":[29],"is":[30,77],"unexpected":[31],"behaviour":[32],"caused":[33],"by":[34,140],"the":[35,80,120,136],"unique":[36,72],"out-of-order":[37],"execution":[38,73],"model":[39],"of":[40,88,105,124],"notebooks.":[41,115],"As":[42],"result,":[44],"face":[47],"various":[48,92],"challenges":[49],"ranging":[50],"from":[51],"notebook":[52,93,142],"correctness,":[53],"reproducibility":[54],"cleaning.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"framework":[63,76,100],"performs":[65],"static":[66],"analysis":[67],"on":[68,101,111],"notebooks,":[69],"incorporating":[70],"semantics.":[74],"Our":[75,116],"general":[78],"sense":[81],"it":[83],"accommodates":[84],"wide":[86],"range":[87],"analyses,":[89],"useful":[90],"use":[94],"cases.":[95],"We":[96],"have":[97,108],"instantiated":[98],"our":[99],"diverse":[103],"set":[104],"analyses":[106],"evaluated":[109],"them":[110],"2211":[112],"real":[113],"world":[114],"evaluation":[117],"demonstrates":[118],"vast":[121],"majority":[122],"(98.7%)":[123],"notebooks":[125],"can":[126],"be":[127],"analysed":[128],"less":[130],"than":[131],"second,":[133],"well":[134],"within":[135],"time":[137],"frame":[138],"required":[139],"clients.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
