{"id":"https://openalex.org/W4393336166","doi":"https://doi.org/10.1145/3650203.3663326","title":"Croissant: A Metadata Format for ML-Ready Datasets","display_name":"Croissant: A Metadata Format for ML-Ready Datasets","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4393336166","doi":"https://doi.org/10.1145/3650203.3663326"},"language":"en","primary_location":{"id":"doi:10.1145/3650203.3663326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650203.3663326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10609/151102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010635924","display_name":"Mubashara Akhtar","orcid":"https://orcid.org/0009-0003-6346-2392"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mubashara Akhtar","raw_affiliation_strings":["King's College London"],"affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103212061","display_name":"Omar Benjelloun","orcid":"https://orcid.org/0000-0002-4173-7709"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Benjelloun","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070550428","display_name":"Costanza Conforti","orcid":"https://orcid.org/0000-0002-9484-9632"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Costanza Conforti","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081552858","display_name":"Pieter Gijsbers","orcid":"https://orcid.org/0000-0001-7346-8075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pieter Gijsbers","raw_affiliation_strings":["TUE &amp; OpenML"],"affiliations":[{"raw_affiliation_string":"TUE &amp; OpenML","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082864285","display_name":"Joan Giner-Miguelez","orcid":"https://orcid.org/0000-0003-2335-6977"},"institutions":[{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joan Giner-Miguelez","raw_affiliation_strings":["Universitat Oberta de Catalunya"],"affiliations":[{"raw_affiliation_string":"Universitat Oberta de Catalunya","institution_ids":["https://openalex.org/I138847295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020711463","display_name":"Nitisha Jain","orcid":"https://orcid.org/0000-0002-7429-7949"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nitisha Jain","raw_affiliation_strings":["King's College London"],"affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002457261","display_name":"Michael Kuchnik","orcid":"https://orcid.org/0000-0002-0805-1828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Kuchnik","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074885928","display_name":"Quentin Lhoest","orcid":"https://orcid.org/0009-0000-7660-3420"},"institutions":[{"id":"https://openalex.org/I4210136376","display_name":"FACE Foundation","ror":"https://ror.org/04121g745","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136376"]},{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quentin Lhoest","raw_affiliation_strings":["Hugging Face"],"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4210136376","https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018423883","display_name":"Pierre Marcenac","orcid":"https://orcid.org/0009-0000-7193-1185"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Marcenac","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002530990","display_name":"Manil Maskey","orcid":"https://orcid.org/0000-0002-5087-6903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manil Maskey","raw_affiliation_strings":["NASA"],"affiliations":[{"raw_affiliation_string":"NASA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053488528","display_name":"Peter Mattson","orcid":"https://orcid.org/0000-0002-5984-238X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Mattson","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084976562","display_name":"Luis Oala","orcid":"https://orcid.org/0000-0002-1379-8627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luis Oala","raw_affiliation_strings":["Dotphoton"],"affiliations":[{"raw_affiliation_string":"Dotphoton","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020689635","display_name":"Pierre Ruyssen","orcid":"https://orcid.org/0009-0006-8506-6464"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Ruyssen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056007385","display_name":"Rajat C. Shinde","orcid":"https://orcid.org/0000-0002-9505-6204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat Shinde","raw_affiliation_strings":["NASA IMPACT &amp; UAH"],"affiliations":[{"raw_affiliation_string":"NASA IMPACT &amp; UAH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046030036","display_name":"Elena Simperl","orcid":"https://orcid.org/0000-0003-1722-947X"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I2802952180","display_name":"Open Data Institute","ror":"https://ror.org/02hr72y72","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802952180"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elena Simperl","raw_affiliation_strings":["King's College London and Open Data Institute"],"affiliations":[{"raw_affiliation_string":"King's College London and Open Data Institute","institution_ids":["https://openalex.org/I2802952180","https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108316601","display_name":"Goeffry Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goeffry Thomas","raw_affiliation_strings":["Google and Kaggle"],"affiliations":[{"raw_affiliation_string":"Google and Kaggle","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101919803","display_name":"Vyacheslav Tykhonov","orcid":"https://orcid.org/0000-0001-9447-9830"},"institutions":[{"id":"https://openalex.org/I4210089348","display_name":"Data Archiving Networked Services (DANS)","ror":"https://ror.org/008pnp284","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I2800991832","https://openalex.org/I4210089348"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Slava Tykhonov","raw_affiliation_strings":["DANS-KNAW"],"affiliations":[{"raw_affiliation_string":"DANS-KNAW","institution_ids":["https://openalex.org/I4210089348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016794035","display_name":"Joaquin Vanschoren","orcid":"https://orcid.org/0000-0001-7044-9805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joaquin Vanschoren","raw_affiliation_strings":["TUE &amp; OpenML"],"affiliations":[{"raw_affiliation_string":"TUE &amp; OpenML","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025786771","display_name":"Jos van der Velde","orcid":"https://orcid.org/0000-0003-0430-1532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos van der Velde","raw_affiliation_strings":["TUE &amp; OpenML"],"affiliations":[{"raw_affiliation_string":"TUE &amp; OpenML","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000410005","display_name":"Steffen Vogler","orcid":"https://orcid.org/0000-0002-7046-0606"},"institutions":[{"id":"https://openalex.org/I4210166400","display_name":"Bayer (France)","ror":"https://ror.org/05cm0es58","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210166400","https://openalex.org/I67348948"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Steffen Vogler","raw_affiliation_strings":["Bayer"],"affiliations":[{"raw_affiliation_string":"Bayer","institution_ids":["https://openalex.org/I4210166400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028220093","display_name":"Carole-Jean Wu","orcid":"https://orcid.org/0000-0002-9032-7239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carole-Jean Wu","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5010635924"],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":18.5017,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.98914809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9911999702453613,"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":0.9911999702453613,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9592999815940857,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9218999743461609,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9327163696289062},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.7834974527359009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6752342581748962},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5228058099746704},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5172791481018066},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5136348605155945},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47918927669525146},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.42206257581710815},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3835506737232208},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3371819853782654},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32506072521209717},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3229633569717407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05526453256607056},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.053124040365219116}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9327163696289062},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.7834974527359009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752342581748962},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5228058099746704},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5172791481018066},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5136348605155945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47918927669525146},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.42206257581710815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3835506737232208},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3371819853782654},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32506072521209717},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3229633569717407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05526453256607056},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.053124040365219116},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1145/3650203.3663326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650203.3663326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.uoc.edu:10609/151102","is_oa":true,"landing_page_url":"http://hdl.handle.net/10609/151102","pdf_url":null,"source":{"id":"https://openalex.org/S7407053569","display_name":"O2 - Repositori Institucional (Universitat Oberta de Catalunya)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2403.19546","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19546","pdf_url":"https://arxiv.org/pdf/2403.19546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/16a4df19-8841-4d99-8df0-eeb6d585f138","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/16a4df19-8841-4d99-8df0-eeb6d585f138","pdf_url":"https://pure.tue.nl/ws/files/343893238/3650203.3663326.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Akhtar, M, Benjelloun, O, Conforti, C, Gijsbers, P, Giner-Miguelez, J, Jain, N, Kuchnik, M, Lhoest, Q, Marcenac, P, Maskey, M, Mattson, P, Oala, L, Ruyssen, P, Shinde, R, Simperl, E, Thomas, G, Tykhonov, S, Vanschoren, J, van der Velde, J, Vogler, S & Wu, C-J 2024, Croissant: A Metadata Format for ML-Ready Datasets. in DEEM '24 : Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning. Association for Computing Machinery, Inc., pp. 1-6. https://doi.org/10.1145/3650203.3663326","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.knaw.nl:openaire_cris_publications/fdacbb0a-ddcf-412e-b7d1-6971115b78ad","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2403.19546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Akthar , M , Benjelloun , O , Conforti , C , Giner Miguelez , J , Jain , N , Kuchnik , M , Lhoest , Q , Marcenac , P , Maskey , M , Mattson , P , Oala , L , Ruyssen , P , Shinde , R , Simperl , E , Thomas , G , Tykhonov , V , Vanschoren , J , Vogler , S & Wu , C-J 2024 ' Croissant: A Metadata Format for ML-Ready Datasets ' Arxiv.org . < https://arxiv.org/abs/2403.19546 >","raw_type":"workingPaper"},{"id":"pmh:oai:pure.knaw.nl:publications/fdacbb0a-ddcf-412e-b7d1-6971115b78ad","is_oa":true,"landing_page_url":"https://pure.knaw.nl/portal/en/publications/fdacbb0a-ddcf-412e-b7d1-6971115b78ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Akthar , M , Benjelloun , O , Conforti , C , Giner Miguelez , J , Jain , N , Kuchnik , M , Lhoest , Q , Marcenac , P , Maskey , M , Mattson , P , Oala , L , Ruyssen , P , Shinde , R , Simperl , E , Thomas , G , Tykhonov , V , Vanschoren , J , Vogler , S & Wu , C-J 2024 ' Croissant: A Metadata Format for ML-Ready Datasets ' Arxiv.org . < https://arxiv.org/abs/2403.19546 >","raw_type":"workingPaper"},{"id":"pmh:oai:pure.tue.nl:publications/16a4df19-8841-4d99-8df0-eeb6d585f138","is_oa":true,"landing_page_url":"https://research.tue.nl/files/343893238/3650203.3663326.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Akhtar, M, Benjelloun, O, Conforti, C, Gijsbers, P, Giner-Miguelez, J, Jain, N, Kuchnik, M, Lhoest, Q, Marcenac, P, Maskey, M, Mattson, P, Oala, L, Ruyssen, P, Shinde, R, Simperl, E, Thomas, G, Tykhonov, S, Vanschoren, J, van der Velde, J, Vogler, S & Wu, C-J 2024, Croissant: A Metadata Format for ML-Ready Datasets. in DEEM '24 : Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning. Association for Computing Machinery, Inc., pp. 1-6. https://doi.org/10.1145/3650203.3663326","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.5281/zenodo.14729679","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14729679","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":"article-journal"},{"id":"doi:10.5281/zenodo.14729680","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14729680","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:openaccess.uoc.edu:10609/151102","is_oa":true,"landing_page_url":"http://hdl.handle.net/10609/151102","pdf_url":null,"source":{"id":"https://openalex.org/S7407053569","display_name":"O2 - Repositori Institucional (Universitat Oberta de Catalunya)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G182602407","display_name":null,"funder_award_id":"952215","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G3716945206","display_name":null,"funder_award_id":"101061441","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4328561246","display_name":null,"funder_award_id":"EP/P025676/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6618363488","display_name":null,"funder_award_id":"101007350","funder_id":"https://openalex.org/F4320327207","funder_display_name":"Electronic Components and Systems for European Leadership"},{"id":"https://openalex.org/G7775410883","display_name":null,"funder_award_id":"101007350","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8079567275","display_name":null,"funder_award_id":"952215","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G820099344","display_name":null,"funder_award_id":"101070000","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320327207","display_name":"Electronic Components and Systems for European Leadership","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334679","display_name":"Research Executive Agency","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2750384547","https://openalex.org/W2911227954","https://openalex.org/W2926805670","https://openalex.org/W3085477028","https://openalex.org/W3118813946","https://openalex.org/W3121991495","https://openalex.org/W4205738517","https://openalex.org/W4226096053","https://openalex.org/W4388964515","https://openalex.org/W6639102338","https://openalex.org/W6749630143","https://openalex.org/W7018086371"],"related_works":["https://openalex.org/W1487702188","https://openalex.org/W2374913837","https://openalex.org/W2460834149","https://openalex.org/W1512114296","https://openalex.org/W2109107360","https://openalex.org/W2354316773","https://openalex.org/W2376038160","https://openalex.org/W2907247951","https://openalex.org/W4205875026","https://openalex.org/W2389651964"],"abstract_inverted_index":{"Data":[0],"is":[1,31,58],"a":[2,14,22],"critical":[3],"resource":[4],"for":[5,25],"Machine":[6],"Learning":[7],"(ML),":[8],"yet":[9],"working":[10],"with":[11],"data":[12,30,52],"remains":[13],"key":[15],"friction":[16],"point.":[17],"This":[18],"paper":[19],"introduces":[20],"Croissant,":[21],"metadata":[23],"format":[24],"datasets":[26,40],"that":[27],"simplifies":[28],"how":[29],"used":[32],"by":[33,61],"ML":[34,51,80],"tools":[35],"and":[36,44,54],"frameworks.":[37,81],"Croissant":[38,57],"makes":[39],"more":[41],"discoverable,":[42],"portable":[43],"interoperable,":[45],"thereby":[46],"addressing":[47],"significant":[48],"challenges":[49],"in":[50],"management":[53],"responsible":[55],"AI.":[56],"already":[59],"supported":[60],"several":[62],"popular":[63,79],"dataset":[64],"repositories,":[65],"spanning":[66],"hundreds":[67],"of":[68,70],"thousands":[69],"datasets,":[71],"ready":[72],"to":[73],"be":[74],"loaded":[75],"into":[76],"the":[77],"most":[78]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2024-03-30T00:00:00"}