{"id":"https://openalex.org/W4411449867","doi":"https://doi.org/10.1145/3729352","title":"Towards Understanding Fine-Grained Programming Mistakes and Fixing Patterns in Data Science","display_name":"Towards Understanding Fine-Grained Programming Mistakes and Fixing Patterns in Data Science","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411449867","doi":"https://doi.org/10.1145/3729352"},"language":"en","primary_location":{"id":"doi:10.1145/3729352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729352","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729352","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108053771","display_name":"Weihao Chen","orcid":"https://orcid.org/0009-0003-9108-8473"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei-Hao Chen","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0009-0003-9108-8473","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005081904","display_name":"Jia Lin Cheoh","orcid":"https://orcid.org/0000-0003-4626-5509"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Lin Cheoh","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0003-4626-5509","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118449374","display_name":"Manthan Keim","orcid":"https://orcid.org/0000-0002-3582-5091"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manthan Keim","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-3582-5091","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089865252","display_name":"Sabine Brunswicker","orcid":"https://orcid.org/0000-0001-8631-0955"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabine Brunswicker","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0001-8631-0955","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437453","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0000-0002-5468-9347"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-5468-9347","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108053771"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.9051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90968073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2","issue":"FSE","first_page":"1824","last_page":"1846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7748713493347168},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5987542271614075},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5510216951370239},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5387083292007446},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5079339146614075},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.5004329681396484},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4972410500049591},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46862083673477173},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4623291492462158},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4616260826587677},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.413925439119339},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.40248823165893555},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.3802032470703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748713493347168},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5987542271614075},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5510216951370239},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5387083292007446},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5079339146614075},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5004329681396484},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4972410500049591},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46862083673477173},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4623291492462158},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4616260826587677},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.413925439119339},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.40248823165893555},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3802032470703125},{"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":1,"locations":[{"id":"doi:10.1145/3729352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729352","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3729352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729352","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W40327287","https://openalex.org/W109452506","https://openalex.org/W841012168","https://openalex.org/W1551385575","https://openalex.org/W1564623840","https://openalex.org/W1992460156","https://openalex.org/W2064766209","https://openalex.org/W2065489029","https://openalex.org/W2087419855","https://openalex.org/W2112433871","https://openalex.org/W2145154883","https://openalex.org/W2151725765","https://openalex.org/W2156723666","https://openalex.org/W2161063493","https://openalex.org/W2182687482","https://openalex.org/W2364861723","https://openalex.org/W2626106541","https://openalex.org/W2768736423","https://openalex.org/W2784241156","https://openalex.org/W2785608539","https://openalex.org/W2794673032","https://openalex.org/W2804093830","https://openalex.org/W2850992922","https://openalex.org/W2883977877","https://openalex.org/W2888018391","https://openalex.org/W2968594320","https://openalex.org/W3012094108","https://openalex.org/W3018392316","https://openalex.org/W3105943882","https://openalex.org/W3125702975","https://openalex.org/W3161042817","https://openalex.org/W3207511826","https://openalex.org/W4205596332","https://openalex.org/W4210788642","https://openalex.org/W4220678421","https://openalex.org/W4223432363","https://openalex.org/W4224991060","https://openalex.org/W4233376690","https://openalex.org/W4234436042","https://openalex.org/W4240052332","https://openalex.org/W4241383990","https://openalex.org/W4247737564","https://openalex.org/W4247950739","https://openalex.org/W4249382987","https://openalex.org/W4250691433","https://openalex.org/W4251334431","https://openalex.org/W4253335432","https://openalex.org/W4253813365","https://openalex.org/W4254188649","https://openalex.org/W4284677512","https://openalex.org/W4285167208","https://openalex.org/W4285784744","https://openalex.org/W4288080276","https://openalex.org/W4296425756","https://openalex.org/W4308642593","https://openalex.org/W4308643319","https://openalex.org/W4309389067","https://openalex.org/W4312469091","https://openalex.org/W4313033767","https://openalex.org/W4313547611","https://openalex.org/W4313563482","https://openalex.org/W4313563767","https://openalex.org/W4366547794","https://openalex.org/W4366548004","https://openalex.org/W4384345708","https://openalex.org/W4386603916","https://openalex.org/W4391558545","https://openalex.org/W4411439849","https://openalex.org/W6982728064"],"related_works":["https://openalex.org/W2969257295","https://openalex.org/W3006945192","https://openalex.org/W2986478207","https://openalex.org/W1976804602","https://openalex.org/W2390554102","https://openalex.org/W4312706861","https://openalex.org/W2909969119","https://openalex.org/W2763289028","https://openalex.org/W2098629748","https://openalex.org/W656101134"],"abstract_inverted_index":{"Programming":[0],"is":[1,57],"an":[2,115],"essential":[3],"activity":[4],"in":[5,41,45],"data":[6,29],"science":[7],"(DS).":[8],"Unlike":[9],"regular":[10],"software":[11,42],"developers,":[12],"DS":[13,24,76,124,145,181],"programmers":[14,25,146],"often":[15],"use":[16],"Jupyter":[17,129],"notebooks":[18],"instead":[19],"of":[20,63,118,122],"conventional":[21],"IDEs.":[22],"Moreover,":[23],"focus":[26],"on":[27],"statistics,":[28],"analytics,":[30],"and":[31,67,85,164],"modeling":[32],"rather":[33],"than":[34],"writing":[35],"production-ready":[36],"code":[37,77,92,107],"following":[38],"best":[39],"practices":[40],"engineering.":[43],"Thus,":[44],"order":[46],"to":[47,52,59,95,150],"provide":[48],"effective":[49],"tool":[50,178],"support":[51,179],"improve":[53],"their":[54,155],"productivity,":[55],"it":[56],"important":[58],"understand":[60,151],"what":[61],"kinds":[62],"errors":[64],"they":[65,69,88],"make":[66],"how":[68],"fix":[70,165],"them.":[71],"Previous":[72],"studies":[73],"have":[74],"analyzed":[75],"from":[78,147],"public":[79],"code-sharing":[80],"platforms":[81],"such":[82],"as":[83],"GitHub":[84],"Kaggle.":[86],"However,":[87],"only":[89],"accounted":[90],"for":[91,175,180],"changes":[93],"committed":[94],"the":[96,111,119,152],"version":[97],"history,":[98],"omitting":[99],"many":[100],"programming":[101,156,162],"mistakes":[102,163],"that":[103,167],"are":[104],"resolved":[105],"before":[106],"commits.":[108],"To":[109],"bridge":[110],"gap,":[112],"we":[113,139],"present":[114],"in-depth":[116],"analysis":[117],"fine-grained":[120],"logs":[121],"a":[123],"competition,":[125],"which":[126],"includes":[127],"390":[128],"Notebooks":[130],"written":[131],"by":[132],"participants":[133],"over":[134],"six":[135],"weeks.":[136],"In":[137],"addition,":[138],"conducted":[140],"semi-structured":[141],"interviews":[142],"with":[143],"10":[144],"different":[148],"domains":[149],"reasons":[153],"behind":[154],"mistakes.":[157],"We":[158],"identified":[159],"several":[160],"unique":[161],"patterns":[166],"had":[168],"not":[169],"been":[170],"reported":[171],"before,":[172],"highlighting":[173],"opportunities":[174],"designing":[176],"new":[177],"programming.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}