{"id":"https://openalex.org/W6912198251","doi":"https://doi.org/10.5281/zenodo.15778357","title":"Dataset for \"Large Language Models for Structuring and Integration of Heterogeneous Data\"","display_name":"Dataset for \"Large Language Models for Structuring and Integration of Heterogeneous Data\"","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W6912198251","doi":"https://doi.org/10.5281/zenodo.15778357"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15778357","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15778357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15778357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bongertmann, Henrik","orcid":null},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bongertmann, Henrik","raw_affiliation_strings":["University of Rostock"],"affiliations":[{"raw_affiliation_string":"University of Rostock","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nast, Benjamin","orcid":"https://orcid.org/0000-0003-4659-9840"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nast, Benjamin","raw_affiliation_strings":["University of Rostock"],"affiliations":[{"raw_affiliation_string":"University of Rostock","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Griesch, Leon","orcid":"https://orcid.org/0000-0002-1946-2016"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Griesch, Leon","raw_affiliation_strings":["University of Rostock"],"affiliations":[{"raw_affiliation_string":"University of Rostock","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rotzoll, Henry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135397","display_name":"Zentrum f\u00fcr Foren in der Grafischen Datenverarbeitung","ror":"https://ror.org/030chcw72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135397"]},{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rotzoll, Henry","raw_affiliation_strings":["Datenverarbeitungszentrum MV GmbH"],"affiliations":[{"raw_affiliation_string":"Datenverarbeitungszentrum MV GmbH","institution_ids":["https://openalex.org/I4210135397","https://openalex.org/I4210088543"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sandkuhl, Kurt","orcid":"https://orcid.org/0000-0002-7431-8412"},"institutions":[{"id":"https://openalex.org/I94616838","display_name":"J\u00f6nk\u00f6ping University","ror":"https://ror.org/03t54am93","country_code":"SE","type":"education","lineage":["https://openalex.org/I94616838"]},{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE","SE"],"is_corresponding":false,"raw_author_name":"Sandkuhl, Kurt","raw_affiliation_strings":["University of Rostock","J\u00f6nk\u00f6ping University"],"affiliations":[{"raw_affiliation_string":"University of Rostock","institution_ids":["https://openalex.org/I4665924"]},{"raw_affiliation_string":"J\u00f6nk\u00f6ping University","institution_ids":["https://openalex.org/I94616838"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4665924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.8824999928474426},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.696399986743927},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.44209998846054077},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41130000352859497},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3327000141143799},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.3012000024318695}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.8824999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368000149726868},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.696399986743927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546000063419342},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15778357","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15778357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15778357","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15778357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"is":[1],"the":[2,5,31,41],"dataset":[3],"for":[4,10],"paper":[6],"\"Large":[7],"Language":[8],"Models":[9],"Structuring":[11],"and":[12],"Integration":[13],"of":[14,24,40],"Heterogeneous":[15],"Data\".":[16],"It":[17],"contains:":[18],"Example":[19],"documents":[20],"(anonymized)":[21],"Comparison":[22],"results":[23],"open-source":[25],"LLMs":[26],"Additional":[27],"material":[28],"employed":[29],"in":[30],"case":[32,42],"study":[33,43],"(e.g.,":[34],"prompt":[35],"or":[36],"JSON":[37],"template)":[38],"Results":[39]},"counts_by_year":[],"updated_date":"2025-12-13T23:11:00.310470","created_date":"2025-10-10T00:00:00"}
