{"id":"https://openalex.org/W6929839357","doi":"https://doi.org/10.5281/zenodo.10667088","title":"ENTRANT: A Large Financial Dataset for Table Understanding","display_name":"ENTRANT: A Large Financial Dataset for Table Understanding","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W6929839357","doi":"https://doi.org/10.5281/zenodo.10667088"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10667088","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10667088","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.10667088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zavitsanos, Elias","orcid":"https://orcid.org/0000-0002-2417-3307"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Zavitsanos, Elias","raw_affiliation_strings":["National Centre of Scientific Research \"Demokritos\""],"raw_orcid":"https://orcid.org/0000-0002-2417-3307","affiliations":[{"raw_affiliation_string":"National Centre of Scientific Research \"Demokritos\"","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mavroeidis, Dimitris","orcid":"https://orcid.org/0000-0001-6602-0520"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Mavroeidis, Dimitris","raw_affiliation_strings":["National Centre of Scientific Research \"Demokritos\""],"raw_orcid":"https://orcid.org/0000-0001-6602-0520","affiliations":[{"raw_affiliation_string":"National Centre of Scientific Research \"Demokritos\"","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Spyropoulou, Eirini","orcid":"https://orcid.org/0009-0000-0478-0022"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Spyropoulou, Eirini","raw_affiliation_strings":["National Centre of Scientific Research \"Demokritos\""],"raw_orcid":"https://orcid.org/0009-0000-0478-0022","affiliations":[{"raw_affiliation_string":"National Centre of Scientific Research \"Demokritos\"","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fergadiotis, Manos","orcid":"https://orcid.org/0000-0002-7657-5156"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Fergadiotis, Manos","raw_affiliation_strings":["National Centre of Scientific Research \"Demokritos\""],"raw_orcid":"https://orcid.org/0000-0002-7657-5156","affiliations":[{"raw_affiliation_string":"National Centre of Scientific Research \"Demokritos\"","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"last","author":{"id":null,"display_name":"Paliouras, Georgios","orcid":"https://orcid.org/0000-0001-9629-2367"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Paliouras, Georgios","raw_affiliation_strings":["National Centre of Scientific Research \"Demokritos\""],"raw_orcid":"https://orcid.org/0000-0001-9629-2367","affiliations":[{"raw_affiliation_string":"National Centre of Scientific Research \"Demokritos\"","institution_ids":["https://openalex.org/I203474044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203474044"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/table","display_name":"Table (database)","score":0.8691999912261963},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6503999829292297},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5795999765396118},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5733000040054321},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.5483999848365784},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8691999912261963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6503999829292297},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4643999934196472},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10667088","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10667088","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.10667088","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10667088","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4776836335659027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"data":[1,17,141],"is":[2,182],"a":[3,49,79,132,146,174,178],"way":[4],"to":[5,37,45,68,93],"structure,":[6],"organize":[7],"and":[8,12,29,71,74,101,123,143,148],"present":[9,16],"information":[10,28,125],"conveniently":[11,66],"effectively.":[13],"Real-world":[14],"tables":[15,90],"in":[18,24,55,131,145,173],"two":[19],"dimensions":[20],"by":[21],"arranging":[22],"cells":[23],"matrices":[25],"that":[26,51,84],"summarize":[27],"facilitate":[30],"side-by-side":[31],"comparisons.":[32],"Recent":[33],"research":[34],"efforts":[35],"aim":[36],"train":[38],"large":[39,63],"models":[40],"with":[41,115,127],"machine":[42],"learning":[43,117],"methods":[44],"understand":[46],"structured":[47],"tables,":[48],"process":[50],"enables":[52],"knowledge":[53],"transfer":[54],"various":[56],"downstream":[57,186],"tasks.":[58],"Model":[59],"pre-training,":[60],"though,":[61],"requires":[62],"tabular":[64],"datasets,":[65],"formatted":[67],"reflect":[69,94],"cell":[70,95,124,187],"table":[72,113,122],"properties":[73],"characteristics.":[75],"This":[76],"paper":[77],"presents":[78],"financial":[80],"dataset,":[81,157],"called":[82],"ENTRANT":[83],"comprises":[85],"millions":[86],"of":[87,161,170,177],"tables.":[88],"The":[89,119],"are":[91],"transformed":[92],"attributes,":[96],"as":[97,99],"well":[98],"positional":[100],"hierarchical":[102],"information.":[103],"Hence,":[104],"they":[105],"facilitate,":[106],"among":[107],"other":[108],"things,":[109],"pre-training":[110,175],"tasks":[111],"for":[112,185],"understanding":[114],"deep":[116],"methods.":[118],"dataset":[120,172],"provides":[121],"along":[126],"the":[128,156,168,171],"corresponding":[129],"metadata":[130],"machine-readable":[133],"JSON":[134],"format.":[135],"Furthermore,":[136],"we":[137,152,166],"have":[138,153],"automated":[139],"all":[140],"processing":[142],"curation":[144],"free":[147],"open-access":[149],"project.":[150],"Moreover,":[151],"technically":[154],"validated":[155],"through":[158],"unit":[159],"testing":[160],"high":[162],"code":[163],"coverage.":[164],"Finally,":[165],"demonstrate":[167],"use":[169],"task":[176],"state-of-the-art":[179],"model,":[180],"which":[181],"also":[183],"used":[184],"classification.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}