{"id":"https://openalex.org/W4313195842","doi":"https://doi.org/10.1109/tkde.2022.3222538","title":"AI Assistants: A Framework for Semi-Automated Data Wrangling","display_name":"AI Assistants: A Framework for Semi-Automated Data Wrangling","publication_year":2022,"publication_date":"2022-11-16","ids":{"openalex":"https://openalex.org/W4313195842","doi":"https://doi.org/10.1109/tkde.2022.3222538"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3222538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3222538","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openaccess.city.ac.uk/id/eprint/29107/1/AIDA_AI%20_Assistants_TKDE_2022.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tomas Petricek","orcid":"https://orcid.org/0000-0002-7242-2208"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tomas Petricek","raw_affiliation_strings":["Charles University, Prague, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7242-2208","affiliations":[{"raw_affiliation_string":"Charles University, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125451","display_name":"Gerrit J. J. van den Burg","orcid":"https://orcid.org/0000-0001-5439-6248"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Gerrit J. J. van den Burg","raw_affiliation_strings":["Alan Turing Institute, London, U.K","Amazon, Slough, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Amazon, Slough, U.K","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069806454","display_name":"Alfredo Naz\u00e1bal","orcid":"https://orcid.org/0000-0002-9414-7139"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alfredo Naz\u00e1bal","raw_affiliation_strings":["Alan Turing Institute, London, U.K","Amazon Development Centre Scotland, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Amazon Development Centre Scotland, Edinburgh, U.K","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026563826","display_name":"Taha Ceritli","orcid":null},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Taha Ceritli","raw_affiliation_strings":["University of Edinburgh and Alan Turing Institute, London, U.K","University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh and Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I125680101","https://openalex.org/I4210128584"]},{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056324053","display_name":"Ernesto Jim\u00e9nez-Ruiz","orcid":"https://orcid.org/0000-0002-9083-4599"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]},{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["GB","NO"],"is_corresponding":false,"raw_author_name":"Ernesto Jim\u00e9nez-Ruiz","raw_affiliation_strings":["City, University of London, London, U.K","University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-9083-4599","affiliations":[{"raw_affiliation_string":"City, University of London, London, U.K","institution_ids":["https://openalex.org/I180825142"]},{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080713659","display_name":"Christopher K. I. Williams","orcid":"https://orcid.org/0000-0002-6270-4703"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher K. I. Williams","raw_affiliation_strings":["University of Edinburgh, Edinburgh, U.K","Alan Turing Institute, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6270-4703","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5645,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90021418,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"9","first_page":"9295","last_page":"9306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9824000000953674,"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/computer-science","display_name":"Computer science","score":0.8492369055747986},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7232367396354675},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.48444274067878723},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47214463353157043},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4191282391548157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3899621069431305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3263414800167084},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25260868668556213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492369055747986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7232367396354675},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.48444274067878723},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47214463353157043},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4191282391548157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3899621069431305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3263414800167084},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25260868668556213},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tkde.2022.3222538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3222538","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:openaccess.city.ac.uk:29107","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/ernesto=2Ejimenez-ruiz.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/29107/1/AIDA_AI%20_Assistants_TKDE_2022.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/78e5ca96-2247-4e4d-b287-497eba42fdbd","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/306059670/AI_Assistants_PETRICEK_DOA30102022_AFV.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Petricek, T, van Den Burg, G J J, Naz\u00e1bal, A, Ceritli, T, Jim\u00e9nez-Ruiz, E & Williams, C K I 2023, 'AI Assistants: A Framework for Semi-Automated Data Wrangling', IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9295-9306. https://doi.org/10.1109/TKDE.2022.3222538","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/78e5ca96-2247-4e4d-b287-497eba42fdbd","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/78e5ca96-2247-4e4d-b287-497eba42fdbd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Petricek, T, van Den Burg, G J J, Naz\u00e1bal, A, Ceritli, T, Jim\u00e9nez-Ruiz, E & Williams, C K I 2023, 'AI Assistants: A Framework for Semi-Automated Data Wrangling', IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9295-9306. https://doi.org/10.1109/TKDE.2022.3222538","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:www.duo.uio.no:10852/98188","is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/98188","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1041-4347","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:openaccess.city.ac.uk:29107","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/ernesto=2Ejimenez-ruiz.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/29107/1/AIDA_AI%20_Assistants_TKDE_2022.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1309768829","display_name":null,"funder_award_id":"EP/N510129/1.","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1929909371","display_name":null,"funder_award_id":"TU/C/000018","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G3504612760","display_name":null,"funder_award_id":"237889","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6517908713","display_name":null,"funder_award_id":"TU/C/000018","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8597009950","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320314707","display_name":"Government of the United Kingdom","ror":"https://ror.org/05wnh3t63"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313195842.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W1970607969","https://openalex.org/W1973008108","https://openalex.org/W1992479406","https://openalex.org/W2046298800","https://openalex.org/W2049309829","https://openalex.org/W2051001073","https://openalex.org/W2056748234","https://openalex.org/W2059216172","https://openalex.org/W2063103859","https://openalex.org/W2064784803","https://openalex.org/W2085610451","https://openalex.org/W2098961002","https://openalex.org/W2132667707","https://openalex.org/W2143677795","https://openalex.org/W2146105230","https://openalex.org/W2153834102","https://openalex.org/W2171332293","https://openalex.org/W2181616869","https://openalex.org/W2222512263","https://openalex.org/W2249895122","https://openalex.org/W2294212155","https://openalex.org/W2421097601","https://openalex.org/W2516678343","https://openalex.org/W2534380090","https://openalex.org/W2612467436","https://openalex.org/W2613390631","https://openalex.org/W2616382011","https://openalex.org/W2750620035","https://openalex.org/W2807685335","https://openalex.org/W2809161078","https://openalex.org/W2898796029","https://openalex.org/W2902696364","https://openalex.org/W2916904544","https://openalex.org/W2939684257","https://openalex.org/W2963967828","https://openalex.org/W2966284335","https://openalex.org/W2971148757","https://openalex.org/W2990427812","https://openalex.org/W3005705150","https://openalex.org/W3010935331","https://openalex.org/W3013003636","https://openalex.org/W3023201182","https://openalex.org/W3030839882","https://openalex.org/W3035623224","https://openalex.org/W3098495036","https://openalex.org/W3099161928","https://openalex.org/W3102186774","https://openalex.org/W3104128335","https://openalex.org/W3120740533","https://openalex.org/W3146259567","https://openalex.org/W4200329746","https://openalex.org/W4213251046","https://openalex.org/W4213251304","https://openalex.org/W4237645110","https://openalex.org/W4287811436","https://openalex.org/W6676014748","https://openalex.org/W6685764666","https://openalex.org/W6686029465","https://openalex.org/W6731864191","https://openalex.org/W6737232052","https://openalex.org/W6740228967","https://openalex.org/W6753559768","https://openalex.org/W6753648510","https://openalex.org/W6781674439"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2348743188","https://openalex.org/W4387423451","https://openalex.org/W2902317490","https://openalex.org/W1741600793","https://openalex.org/W2096879929","https://openalex.org/W2593663830","https://openalex.org/W2381703089","https://openalex.org/W2046628353","https://openalex.org/W2354233396"],"abstract_inverted_index":{"Data":[0],"wrangling":[1,39,69,119],"tasks":[2,120,171],"such":[3],"as":[4,104],"obtaining":[5],"and":[6,15,35,43,95,121,152,163],"linking":[7],"data":[8,13,26,38,57,68,75,102,118,128,136],"from":[9],"various":[10],"sources,":[11],"transforming":[12],"formats,":[14],"correcting":[16],"erroneous":[17],"records,":[18],"can":[19],"constitute":[20],"up":[21],"to":[22,55,127,169,176],"80%":[23],"of":[24,32,51,92],"typical":[25],"engineering":[27],"work.":[28],"Despite":[29],"the":[30,63,79,85,90,109,140,161],"rise":[31],"machine":[33],"learning":[34],"artificial":[36],"intelligence,":[37],"remains":[40],"a":[41,49,66,73,181],"tedious":[42],"manual":[44],"task.":[45],"We":[46,87,111,145,158],"introduceAI":[47],"assistants,":[48],"class":[50],"semi-automatic":[52],"interactive":[53,164],"tools":[54,99],"streamline":[56],"wrangling.":[58],"An":[59],"AI":[60,93,113,123,148],"assistant":[61],"guides":[62],"analyst":[64],"through":[65,82,154],"specific":[67],"task":[70],"by":[71,138],"recommending":[72],"suitable":[74],"transformation":[76],"that":[77,100,160,172],"respects":[78],"constraints":[80],"obtained":[81],"interaction":[83],"with":[84,180],"analyst.":[86],"formally":[88],"define":[89],"structure":[91,142],"assistants":[94,114,124,149],"describe":[96],"how":[97],"existing":[98],"treat":[101],"cleaning":[103],"an":[105,131],"optimization":[106],"problem":[107],"fit":[108],"definition.":[110],"implement":[112],"for":[115,135],"four":[116],"common":[117,141],"make":[122],"easily":[125],"accessible":[126],"analysts":[129],"in":[130],"open-source":[132],"notebook":[133],"environment":[134],"science,":[137],"leveraging":[139],"they":[143],"follow.":[144],"evaluate":[146],"our":[147],"both":[150],"quantitatively":[151],"qualitatively":[153],"three":[155],"example":[156],"scenarios.":[157],"show":[159],"unified":[162],"design":[165],"makes":[166],"it":[167],"easy":[168],"perform":[170],"would":[173],"be":[174],"difficult":[175],"do":[177],"manually":[178],"or":[179],"fully":[182],"automatic":[183],"tool.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-10T00:00:00"}
