{"id":"https://openalex.org/W4399175215","doi":"https://doi.org/10.1145/3654975","title":"SchemaPile: A Large Collection of Relational Database Schemas","display_name":"SchemaPile: A Large Collection of Relational Database Schemas","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4399175215","doi":"https://doi.org/10.1145/3654975"},"language":"en","primary_location":{"id":"doi:10.1145/3654975","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654975","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654975","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3654975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005496964","display_name":"Till D\u00f6hmen","orcid":"https://orcid.org/0000-0001-7483-0099"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Till D\u00f6hmen","raw_affiliation_strings":["University of Amsterdam, Amsterdam, NL"],"raw_orcid":"https://orcid.org/0000-0001-7483-0099","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, NL","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098946115","display_name":"Radu Geacu","orcid":"https://orcid.org/0009-0009-6728-3379"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Radu Geacu","raw_affiliation_strings":["University of Amsterdam, Amsterdam, NL"],"raw_orcid":"https://orcid.org/0009-0009-6728-3379","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, NL","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058441702","display_name":"Madelon Hulsebos","orcid":"https://orcid.org/0000-0002-0949-7290"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madelon Hulsebos","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-0949-7290","affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["University of Amsterdam, Amsterdam, NL"],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, NL","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5779,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92719502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10260","display_name":"Software Engineering Research","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8348373174667358},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.6493786573410034},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.602604329586029},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5368118286132812},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4737361669540405},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.47222235798835754},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.46120044589042664},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4497893452644348},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4461987018585205},{"id":"https://openalex.org/keywords/database-model","display_name":"Database model","score":0.42875465750694275},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.416670560836792},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33032143115997314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348373174667358},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.6493786573410034},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.602604329586029},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5368118286132812},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4737361669540405},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.47222235798835754},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.46120044589042664},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4497893452644348},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4461987018585205},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.42875465750694275},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.416670560836792},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33032143115997314},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3654975","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654975","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654975","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:cwi.nl:34763","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/34763","pdf_url":"https://ir.cwi.nl/pub/34763/34763.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/0b5b426f-038c-437a-8ccb-18efd7e7a118","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/schemapile-a-large-collection-of-relational-database-schemas(0b5b426f-038c-437a-8ccb-18efd7e7a118).html","pdf_url":"https://pure.uva.nl/ws/files/228009965/SchemaPile.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"D\u00f6hmen, T, Geacu, R, Hulsebos, M & Schelter, S 2024, 'SchemaPile: A Large Collection of Relational Database Schemas', Proceedings of the ACM on Management of Data, vol. 2, no. 3, 172. https://doi.org/10.1145/3654975","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:cwi.nl:34880","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/34880","pdf_url":null,"source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1145/3654975","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654975","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654975","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399175215.pdf","grobid_xml":"https://content.openalex.org/works/W4399175215.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2092364718","https://openalex.org/W2108223890","https://openalex.org/W2341748398","https://openalex.org/W2435931733","https://openalex.org/W2544486974","https://openalex.org/W2623925395","https://openalex.org/W2795089200","https://openalex.org/W2796196104","https://openalex.org/W2806056912","https://openalex.org/W2889249015","https://openalex.org/W2890431379","https://openalex.org/W2893303656","https://openalex.org/W2949054050","https://openalex.org/W2970992672","https://openalex.org/W2999751364","https://openalex.org/W3174181645","https://openalex.org/W3175111921","https://openalex.org/W4281795225","https://openalex.org/W4365456672","https://openalex.org/W4381326864","https://openalex.org/W4381621958","https://openalex.org/W4382202606","https://openalex.org/W4386128198","https://openalex.org/W4393791010"],"related_works":["https://openalex.org/W1016652228","https://openalex.org/W2591891926","https://openalex.org/W1588786827","https://openalex.org/W279222092","https://openalex.org/W1502610062","https://openalex.org/W2153455914","https://openalex.org/W2007556552","https://openalex.org/W2460926837","https://openalex.org/W2512945146","https://openalex.org/W2389923540"],"abstract_inverted_index":{"Access":[0],"to":[1,36,78,109,121,201],"fine-grained":[2],"schema":[3,72,177],"information":[4,30,73],"is":[5,31],"crucial":[6],"for":[7,19,45,162,212,232],"understanding":[8],"how":[9,64,75],"relational":[10],"databases":[11],"are":[12,66,101],"designed":[13],"and":[14,18,51,104,159,190,221,230,235],"used":[15],"in":[16,180],"practice,":[17],"building":[20],"systems":[21],"that":[22],"help":[23],"users":[24],"interact":[25],"with":[26,145],"them.":[27],"Furthermore,":[28],"such":[29,58],"required":[32],"as":[33,59,81,83,183,185],"training":[34],"data":[35,47,49,86,160,206,231],"leverage":[37],"the":[38,92,174,197,228],"potential":[39,198],"of":[40,130,176,199,205],"large":[41],"language":[42,53,189],"models":[43],"(LLMs)":[44],"improving":[46,217],"preparation,":[48],"integration":[50],"natural":[52],"querying.":[54],"Existing":[55],"single-table":[56],"corpora":[57],"GitTables":[60],"provide":[61],"insights":[62],"into":[63],"tables":[65,76,144],"structured":[67],"in-the-wild,":[68],"but":[69],"lack":[70],"detailed":[71],"about":[74],"relate":[77],"each":[79],"other,":[80],"well":[82,184],"metadata":[84,178],"like":[85],"types":[87],"or":[88],"integrity":[89,157],"constraints.":[90],"On":[91],"other":[93],"hand,":[94],"existing":[95],"multi-table":[96],"(or":[97],"database":[98,117,132],"schema)":[99],"datasets":[100],"rather":[102],"small":[103],"attribute-poor,":[105],"leaving":[106],"it":[107],"unclear":[108],"what":[110],"extent":[111],"they":[112],"actually":[113],"represent":[114],"typical":[115],"real-world":[116],"schemas.":[118],"In":[119,193],"order":[120],"address":[122],"these":[123],"challenges,":[124],"we":[125,195],"present":[126],"SchemaPile,":[127],"a":[128,203,236],"corpus":[129],"221,171":[131],"schemas,":[133],"extracted":[134],"from":[135],"SQL":[136,224],"files":[137],"on":[138,173],"GitHub.":[139],"It":[140],"contains":[141],"1.7":[142],"million":[143,147,156],"10":[146],"column":[148],"definitions,":[149],"700":[150],"thousand":[151,166],"foreign":[152,214],"key":[153,215],"relationships,":[154],"seven":[155],"constraints,":[158],"content":[161],"more":[163],"than":[164],"340":[165],"tables.":[167],"We":[168,226],"conduct":[169],"an":[170],"in-depth":[171],"analysis":[172],"millions":[175],"properties":[179],"our":[181],"corpus,":[182],"its":[186],"highly":[187],"diverse":[188],"topic":[191],"distribution.":[192],"addition,":[194],"showcase":[196],"\\corpus":[200],"improve":[202],"variety":[204],"management":[207],"applications,":[208],"e.g.,":[209],"fine-tuning":[210],"LLMs":[211],"schema-only":[213],"detection,":[216],"CSV":[218],"header":[219],"detection":[220],"evaluating":[222],"multi-dialect":[223],"parsers.":[225],"publish":[227],"code":[229],"recreating":[233],"SchemaPile":[234],"permissively":[237],"licensed":[238],"subset":[239],"SchemaPile-Perm.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-05-31T00:00:00"}
