{"id":"https://openalex.org/W4386768511","doi":"https://doi.org/10.14778/3611540.3611610","title":"To UDFs and Beyond: Demonstration of a Fully Decomposed Data Processor for General Data Wrangling Tasks","display_name":"To UDFs and Beyond: Demonstration of a Fully Decomposed Data Processor for General Data Wrangling Tasks","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4386768511","doi":"https://doi.org/10.14778/3611540.3611610"},"language":"en","primary_location":{"id":"doi:10.14778/3611540.3611610","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611610","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5025579996","display_name":"Nico Sch\u00e4fer","orcid":null},"institutions":[{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nico Sch\u00e4fer","raw_affiliation_strings":["RPTU Kaiserslautern-Landau"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau","institution_ids":["https://openalex.org/I4387152675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075220789","display_name":"Damjan Gjurovski","orcid":"https://orcid.org/0000-0002-1296-5745"},"institutions":[{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Damjan Gjurovski","raw_affiliation_strings":["RPTU Kaiserslautern-Landau"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau","institution_ids":["https://openalex.org/I4387152675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048757078","display_name":"Angjela Davitkova","orcid":null},"institutions":[{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Angjela Davitkova","raw_affiliation_strings":["RPTU Kaiserslautern-Landau"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau","institution_ids":["https://openalex.org/I4387152675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043223305","display_name":"Sebastian Michel","orcid":"https://orcid.org/0000-0001-6636-2694"},"institutions":[{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Michel","raw_affiliation_strings":["RPTU Kaiserslautern-Landau"],"affiliations":[{"raw_affiliation_string":"RPTU Kaiserslautern-Landau","institution_ids":["https://openalex.org/I4387152675"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025579996"],"corresponding_institution_ids":["https://openalex.org/I4387152675"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15457667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"12","first_page":"4018","last_page":"4021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9940999746322632,"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":0.9940999746322632,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9934999942779541,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8467986583709717},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8447602391242981},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.768444299697876},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5157825946807861},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.45154377818107605},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4414340853691101},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37734436988830566},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34599706530570984},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3349347710609436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2778417468070984},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.27056002616882324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467986583709717},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8447602391242981},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.768444299697876},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5157825946807861},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.45154377818107605},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4414340853691101},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37734436988830566},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34599706530570984},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3349347710609436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2778417468070984},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27056002616882324},{"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:10.14778/3611540.3611610","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611540.3611610","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2044849727","https://openalex.org/W2112485457","https://openalex.org/W2266823300","https://openalex.org/W2979826702","https://openalex.org/W3030533359","https://openalex.org/W3164278511","https://openalex.org/W3173732543","https://openalex.org/W3175890395","https://openalex.org/W4285160575","https://openalex.org/W4289866506"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W2188981919","https://openalex.org/W3084909426"],"abstract_inverted_index":{"While":[0],"existing":[1],"data":[2,11,61,65,140],"management":[3],"solutions":[4],"try":[5],"to":[6,48,77,120,126,135,138],"keep":[7],"up":[8],"with":[9,90],"novel":[10],"formats":[12],"and":[13,40,96,99,116,122],"features,":[14],"a":[15,35,45,58],"myriad":[16],"of":[17,37,57,72,146],"valuable":[18],"functionality":[19],"is":[20,34],"often":[21],"only":[22],"accessible":[23],"via":[24],"programming":[25],"language":[26],"libraries.":[27],"Particularly":[28],"for":[29,63],"machine":[30,51],"learning":[31],"tasks,":[32],"there":[33],"wealth":[36],"pre-trained":[38],"models":[39],"easy-to-use":[41],"libraries":[42],"that":[43,66,131],"allow":[44],"wide":[46],"audience":[47,119],"harness":[49],"state-of-the-art":[50],"learning.":[52],"We":[53],"propose":[54],"the":[55,82,87,118],"demonstration":[56],"highly":[59],"modularized":[60],"processor":[62],"semi-structured":[64],"can":[67,112],"be":[68,113],"extended":[69],"by":[70],"means":[71],"plain":[73],"Python":[74],"scripts.":[75],"Next":[76],"commonly":[78],"supported":[79],"user-defined":[80,110],"functions,":[81],"deep":[83],"decomposition":[84],"allows":[85],"augmenting":[86],"core":[88],"engine":[89],"additional":[91],"index":[92],"structures,":[93],"customized":[94],"import":[95],"export":[97],"routines,":[98],"custom":[100,124],"aggregation":[101],"functions.":[102],"For":[103],"several":[104],"use":[105],"cases,":[106],"we":[107,132],"detail":[108],"how":[109],"modules":[111],"quickly":[114],"realized":[115],"invite":[117],"write":[121],"apply":[123],"code,":[125],"tailor":[127],"provided":[128],"code":[129],"snippets":[130],"bring":[133],"along":[134],"own":[136],"preferences":[137],"solve":[139],"analytics":[141],"tasks":[142],"involving":[143],"sentiment":[144],"analysis":[145],"Twitter":[147],"tweets.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}