{"id":"https://openalex.org/W4404181231","doi":"https://doi.org/10.14778/3685800.3685897","title":"DataLoom: Simplifying Data Loading with LLMs","display_name":"DataLoom: Simplifying Data Loading with LLMs","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181231","doi":"https://doi.org/10.14778/3685800.3685897"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685897","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685897","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/A5075037947","display_name":"Alexander van Renen","orcid":"https://orcid.org/0000-0002-6365-4592"},"institutions":[{"id":"https://openalex.org/I4210089351","display_name":"Universidad Tecnol\u00f3gica Nicarag\u00fcense","ror":"https://ror.org/008rn4f38","country_code":"NI","type":"education","lineage":["https://openalex.org/I4210089351"]}],"countries":["NI"],"is_corresponding":false,"raw_author_name":"Alexander van Renen","raw_affiliation_strings":["UTN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTN","institution_ids":["https://openalex.org/I4210089351"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029098584","display_name":"Mihail Stoian","orcid":"https://orcid.org/0000-0002-8843-3374"},"institutions":[{"id":"https://openalex.org/I4210089351","display_name":"Universidad Tecnol\u00f3gica Nicarag\u00fcense","ror":"https://ror.org/008rn4f38","country_code":"NI","type":"education","lineage":["https://openalex.org/I4210089351"]}],"countries":["NI"],"is_corresponding":false,"raw_author_name":"Mihail Stoian","raw_affiliation_strings":["UTN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTN","institution_ids":["https://openalex.org/I4210089351"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046188245","display_name":"Andreas Kipf","orcid":"https://orcid.org/0000-0003-3463-0564"},"institutions":[{"id":"https://openalex.org/I4210089351","display_name":"Universidad Tecnol\u00f3gica Nicarag\u00fcense","ror":"https://ror.org/008rn4f38","country_code":"NI","type":"education","lineage":["https://openalex.org/I4210089351"]}],"countries":["NI"],"is_corresponding":false,"raw_author_name":"Andreas Kipf","raw_affiliation_strings":["UTN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTN","institution_ids":["https://openalex.org/I4210089351"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7361,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9314296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"17","issue":"12","first_page":"4449","last_page":"4452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9836000204086304,"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":0.9836000204086304,"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/T11719","display_name":"Data Quality and Management","score":0.9815000295639038,"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/T11937","display_name":"Research Data Management Practices","score":0.9731000065803528,"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":0.3720594644546509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3720594644546509}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685897","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685897","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":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2064766209","https://openalex.org/W2126848435","https://openalex.org/W2232417456","https://openalex.org/W2430301697","https://openalex.org/W2948163032","https://openalex.org/W2949054050","https://openalex.org/W2970992672","https://openalex.org/W4378980478","https://openalex.org/W4389315083"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Schema":[0],"discovery":[1,131,160,181],"and":[2,30,98,112,147,161,182],"data":[3,11,37,61,162,183],"loading":[4,163,184],"is":[5,102],"a":[6,19,43,67,82,156],"crucial":[7],"step":[8],"in":[9,22,185],"any":[10],"analysis":[12],"pipeline.":[13],"While":[14],"this":[15,74,110,176],"used":[16],"to":[17,87,103,132,169],"be":[18,95],"rare":[20],"task,":[21],"the":[23,60,63,78,105,116,139,144,151,167],"highly":[24],"dynamic":[25],"field":[26],"of":[27,36,59,70,80,85,109,118,141],"machine":[28],"learning":[29],"modern":[31,179],"business":[32],"intelligence":[33],"on":[34,53,62,178],"top":[35],"lakes,":[38],"today":[39],"it":[40],"has":[41],"become":[42],"frequent,":[44],"but":[45],"often":[46,51],"underestimated,":[47],"activity.":[48],"Existing":[49],"tools":[50],"focus":[52],"single":[54],"files,":[55],"presume":[56],"prior":[57],"knowledge":[58],"user's":[64],"side":[65],"or":[66],"significant":[68],"amount":[69],"manual":[71],"labor.":[72],"In":[73],"paper,":[75],"we":[76],"improve":[77],"process":[79,111],"mapping":[81],"\"chaotic\"":[83],"set":[84],"files":[86],"an":[88],"initial":[89],"database":[90],"schema":[91,159,180],"that":[92,165,191],"can":[93],"then":[94],"iteratively":[96],"refined":[97],"loaded.":[99],"The":[100],"idea":[101],"take":[104],"previously":[106],"tedious":[107],"parts":[108],"automate":[113],"them":[114],"through":[115],"use":[117,140],"Large":[119],"Language":[120],"Models":[121],"(LLMs)":[122],"while":[123],"leaving":[124],"already":[125],"well-understood":[126],"problems":[127,146],"such":[128],"as":[129,193],"constraint":[130],"existing":[133],"algorithms.":[134],"We":[135,174],"thus":[136],"carefully":[137],"orchestrate":[138],"LLMs":[142],"for":[143,150,172],"\"soft\"":[145],"traditional":[148],"algorithms":[149],"\"hard\"":[152],"problems.":[153],"This":[154],"creates":[155],"more":[157],"seamless":[158],"experience":[164],"minimizes":[166],"time":[168],"first":[170],"insight":[171],"users.":[173],"show":[175],"vision":[177],"our":[186,194],"web-based":[187],"prototype":[188],"called":[189],"DataLoom":[190],"serves":[192],"demonstration.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}