{"id":"https://openalex.org/W6930271676","doi":"https://doi.org/10.5281/zenodo.11559814","title":"WikiDBs - A Large-Scale Corpus Of Relational Databases From Wikidata","display_name":"WikiDBs - A Large-Scale Corpus Of Relational Databases From Wikidata","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W6930271676","doi":"https://doi.org/10.5281/zenodo.11559814"},"language":"en","primary_location":{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:153589","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Vogel=3ALiane=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.11559814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Vogel, Liane","orcid":"https://orcid.org/0000-0001-9768-8873"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vogel, Liane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bodensohn, Jan-Micha","orcid":"https://orcid.org/0000-0003-4884-0300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bodensohn, Jan-Micha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Binnig, Carsten","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binnig, Carsten","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":{"id":"https://openalex.org/T10105","display_name":"Osteoarthritis Treatment and Mechanisms","score":0.9006999731063843,"subfield":{"id":"https://openalex.org/subfields/2745","display_name":"Rheumatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10105","display_name":"Osteoarthritis Treatment and Mechanisms","score":0.9006999731063843,"subfield":{"id":"https://openalex.org/subfields/2745","display_name":"Rheumatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11591","display_name":"NF-\u03baB Signaling Pathways","score":0.006000000052154064,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11736","display_name":"Histone Deacetylase Inhibitors Research","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6704999804496765},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.49619999527931213},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4620000123977661},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.4203000068664551},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41990000009536743},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.37209999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6704999804496765},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5871999859809875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.49619999527931213},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41990000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C103593891","wikidata":"https://www.wikidata.org/wiki/Q624546","display_name":"Entity\u2013relationship model","level":3,"score":0.36899998784065247},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:153589","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Vogel=3ALiane=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"doi:10.5281/zenodo.11559814","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11559814","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.11559814","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11559814","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"WikiDBs":[0,36,52],"is":[1,23],"an":[2],"open-source":[3],"corpus":[4,22],"of":[5,33,93],"100,000":[6,77],"relational":[7],"databases.":[8,35],"We":[9,102],"aim":[10],"to":[11,29,107],"support":[12],"research":[13],"on":[14,18,25],"tabular":[15],"representation":[16],"learning":[17],"multi-table":[19],"data.":[20],"The":[21,62,76],"based":[24],"Wikidata":[26],"and":[27,70],"aims":[28],"follow":[30],"certain":[31],"characteristics":[32],"real-world":[34],"was":[37],"published":[38],"as":[39,57,59,67,74],"a":[40,105],"spotlight":[41],"paper":[42],"at":[43,49],"the":[44,54,99,109],"Dataset":[45],"&":[46],"Benchmarks":[47],"track":[48],"NeurIPS":[50],"2024.":[51],"contains":[53],"database":[55,63,72],"schemas,":[56],"well":[58],"table":[60],"contents.":[61],"tables":[64],"are":[65,79,96],"provided":[66],"CSV":[68],"files,":[69],"each":[71],"schema":[73],"JSON.":[75],"databases":[78,86,110],"available":[80],"in":[81],"five":[82],"splits,":[83],"containing":[84],"20k":[85],"each.":[87],"In":[88],"total,":[89],"around":[90],"165":[91],"GB":[92],"disk":[94],"space":[95],"needed":[97],"for":[98],"full":[100],"corpus.":[101],"also":[103],"provide":[104],"script":[106],"convert":[108],"into":[111],"SQLite.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
