{"id":"https://openalex.org/W4403536355","doi":"https://doi.org/10.1145/3691620.3695503","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","display_name":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403536355","doi":"https://doi.org/10.1145/3691620.3695503"},"language":"en","primary_location":{"id":"doi:10.1145/3691620.3695503","doi":"https://doi.org/10.1145/3691620.3695503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695503","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3691620.3695503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040653412","display_name":"Junjie Huang","orcid":"https://orcid.org/0009-0004-6962-5292","observed_orcids":["https://orcid.org/0009-0004-6962-5292"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0004-6962-5292","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060364305","display_name":"Daya Guo","orcid":"https://orcid.org/0009-0008-0822-1517","observed_orcids":["https://orcid.org/0009-0008-0822-1517"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daya Guo","raw_affiliation_strings":["Sun-yat Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-0822-1517","affiliations":[{"raw_affiliation_string":"Sun-yat Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063667052","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0002-5933-6620","observed_orcids":["https://orcid.org/0000-0002-5933-6620"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-5933-6620","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042468232","display_name":"Jiazhen Gu","orcid":"https://orcid.org/0000-0002-5831-9474","observed_orcids":["https://orcid.org/0000-0002-5831-9474"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiazhen Gu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5831-9474","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112547849","display_name":"Shuai Lu","orcid":"https://orcid.org/0000-0001-7466-2064","observed_orcids":["https://orcid.org/0000-0001-7466-2064"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7466-2064","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020203532","display_name":"Jeevana Priya Inala","orcid":"https://orcid.org/0000-0003-1843-589X","observed_orcids":["https://orcid.org/0000-0003-1843-589X"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeevana Priya Inala","raw_affiliation_strings":["Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0003-1843-589X","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807460","display_name":"Cong Yan","orcid":"https://orcid.org/0009-0001-3596-4083","observed_orcids":["https://orcid.org/0009-0001-3596-4083"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Yan","raw_affiliation_strings":["Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0009-0001-3596-4083","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-2058-9348","observed_orcids":["https://orcid.org/0000-0002-2058-9348"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-2058-9348","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674","observed_orcids":["https://orcid.org/0000-0002-3387-4674"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3387-4674","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069596903","display_name":"Michael Rung-Tsong Lyu","orcid":"https://orcid.org/0000-0002-3666-5798","observed_orcids":["https://orcid.org/0000-0002-3666-5798"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Michael R. Lyu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3666-5798","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9339,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8834667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1282","last_page":"1294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9603999853134155,"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":0.9603999853134155,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.012000000104308128,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.0034000000450760126,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-wrangling","display_name":"data wrangling","score":0.9850000143051147},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/computational-notebooks","display_name":"computational notebooks","score":0.9909999966621399},{"id":"https://openalex.org/keywords/data-context","display_name":"data context","score":0.8669999837875366},{"id":"https://openalex.org/keywords/textual-context","display_name":"textual context","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726658582687378},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6260471343994141},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6219860911369324},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5069952011108398},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1915697455406189},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3691620.3695503","doi":"https://doi.org/10.1145/3691620.3695503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695503","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.13551","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.13551","pdf_url":"https://arxiv.org/pdf/2409.13551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.13551","doi":"https://doi.org/10.48550/arxiv.2409.13551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.13551","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3691620.3695503","doi":"https://doi.org/10.1145/3691620.3695503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691620.3695503","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6361378377","display_name":null,"funder_award_id":"14206921","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403536355.pdf","grobid_xml":"https://content.openalex.org/works/W4403536355.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W2144951274","https://openalex.org/W2146105230","https://openalex.org/W2342249984","https://openalex.org/W2751448157","https://openalex.org/W2796040126","https://openalex.org/W2890114759","https://openalex.org/W2964315653","https://openalex.org/W2970004377","https://openalex.org/W2980180246","https://openalex.org/W3001279689","https://openalex.org/W3012792922","https://openalex.org/W3089307846","https://openalex.org/W3098605233","https://openalex.org/W3118781290","https://openalex.org/W3125702975","https://openalex.org/W3126095862","https://openalex.org/W3163379266","https://openalex.org/W3170092793","https://openalex.org/W3175200128","https://openalex.org/W3176015924","https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W3198685994","https://openalex.org/W3202191909","https://openalex.org/W3207511826","https://openalex.org/W3207647313","https://openalex.org/W4221166113","https://openalex.org/W4221166942","https://openalex.org/W4226018502","https://openalex.org/W4226325640","https://openalex.org/W4226496243","https://openalex.org/W4252980914","https://openalex.org/W4256028358","https://openalex.org/W4283210053","https://openalex.org/W4284676027","https://openalex.org/W4284677512","https://openalex.org/W4285483825","https://openalex.org/W4286530314","https://openalex.org/W4288055447","https://openalex.org/W4288804596","https://openalex.org/W4315706637","https://openalex.org/W4317716303","https://openalex.org/W4368754606","https://openalex.org/W4376167329","https://openalex.org/W4384155659","https://openalex.org/W4384918448","https://openalex.org/W4385565416","https://openalex.org/W4385571808","https://openalex.org/W4385572707","https://openalex.org/W4385573853","https://openalex.org/W4386185625","https://openalex.org/W4387561528","https://openalex.org/W4387885999","https://openalex.org/W4388483373","https://openalex.org/W4389519979","https://openalex.org/W4391156274","https://openalex.org/W4391272793","https://openalex.org/W4391682392","https://openalex.org/W4396833635","https://openalex.org/W4400582422","https://openalex.org/W4400582976","https://openalex.org/W4402410044","https://openalex.org/W4403210636","https://openalex.org/W4406688098"],"related_works":["https://openalex.org/W4210294742","https://openalex.org/W4409747213","https://openalex.org/W4399117322","https://openalex.org/W3011590361","https://openalex.org/W7167672319","https://openalex.org/W4313195842","https://openalex.org/W7130713371","https://openalex.org/W4403704402","https://openalex.org/W4403104729","https://openalex.org/W4399531177"],"abstract_inverted_index":{"Data":[0],"wrangling,":[1],"the":[2,26,30,55,84,102],"process":[3,33],"of":[4,54,80],"preparing":[5],"raw":[6],"data":[7,21,31,47,67],"for":[8,104],"further":[9],"analysis":[10,75],"in":[11,20,59],"computational":[12],"notebooks,":[13,60],"is":[14],"a":[15,51],"crucial":[16],"yet":[17],"time-consuming":[18],"step":[19],"science.":[22],"Code":[23],"generation":[24],"has":[25],"potential":[27],"to":[28,34,99],"automate":[29],"wrangling":[32,48,106],"reduce":[35],"analysts'":[36],"overhead":[37],"by":[38],"translating":[39],"user":[40],"intents":[41],"into":[42,77],"executable":[43],"code.":[44],"Precisely":[45],"generating":[46],"code":[49,64,81,96,107],"necessitates":[50],"comprehensive":[52],"consideration":[53],"rich":[56],"context":[57,65],"present":[58],"including":[61],"textual":[62],"context,":[63],"and":[66],"context.":[68],"However,":[69],"notebooks":[70],"often":[71],"interleave":[72],"multiple":[73],"non-linear":[74],"tasks":[76],"linear":[78],"sequence":[79],"blocks,":[82],"where":[83],"contextual":[85],"dependencies":[86],"are":[87],"not":[88],"clearly":[89],"reflected.":[90],"Directly":[91],"training":[92],"models":[93],"with":[94],"source":[95],"blocks":[97],"fails":[98],"fully":[100],"exploit":[101],"contexts":[103],"accurate":[105],"generation.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-10-19T00:00:00"}