{"id":"https://openalex.org/W6968278438","doi":"https://doi.org/10.5281/zenodo.13846588","title":"MULTITuDEv2","display_name":"MULTITuDEv2","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W6968278438","doi":"https://doi.org/10.5281/zenodo.13846588"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.13846588","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13846588","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.13846588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Macko, Dominik","orcid":"https://orcid.org/0000-0002-8235-2004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Macko, Dominik","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8235-2004","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Moro, Robert","orcid":"https://orcid.org/0000-0002-3052-8290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moro, Robert","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3052-8290","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Uchendu, Adaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uchendu, Adaku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Srba, Ivan","orcid":"https://orcid.org/0000-0003-3511-5337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srba, Ivan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3511-5337","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lucas, Jason Samuel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas, Jason Samuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yamashita, Michiharu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamashita, Michiharu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Irtiza Tripto, Nafis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irtiza Tripto, Nafis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lee, Dongwon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Dongwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Simko, Jakub","orcid":"https://orcid.org/0000-0003-0239-4237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simko, Jakub","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0239-4237","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Bielikova, Maria","orcid":"https://orcid.org/0000-0003-4105-3494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bielikova, Maria","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4105-3494","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/scripting-language","display_name":"Scripting language","score":0.7494000196456909},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.679099977016449},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.608299970626831},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.42080000042915344},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38839998841285706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530999779701233},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.679099977016449},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.608299970626831},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.13846588","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13846588","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.13846588","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13846588","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":[{"id":"https://openalex.org/G5915888644","display_name":"Vital IntelliGence to Investigate ILlegAl DisiNformaTion","funder_award_id":"101073921","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7381952728","display_name":"AI-CODE - AI services for COntinuous trust in emerging Digital Environments","funder_award_id":"101135437","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"MULTITuDEv2":[0],"is":[1],"a":[2,56,194,197,210,215,257,337],"dataset":[3,60,87,107,118,170,224,262],"for":[4,51,185,189,225,330],"multilingual":[5],"machine-generated":[6,190,343],"text":[7,180,204,274,280,292,334],"detection":[8],"benchmark,":[9],"described":[10,75,133],"in":[11,24,55,65,76,88,94,149,165,293,301,349],"the":[12,77,100,106,117,121,129,146,150,159,166,172,203,206,223,226,235,241,244,252,260,267,282,286,294,298,302,308,312],"EMNLP":[13],"2023":[14],"conference":[15,81],"paper.":[16,82,101],"It":[17],"consists":[18,108],"of":[19,43,105,109,116,145,222,228,243,251,266,307,322,355],"7992":[20,368,400],"human-written":[21,186,211,333],"news":[22,44,264],"texts":[23,33,69,161,316],"11":[25],"languages":[26],"subsampled":[27],"from":[28,278],"MassiveSumm,":[29],"accompanied":[30],"by":[31,35,67,138,281,285,336],"66089":[32,371],"generated":[34,202],"8":[36],"large":[37,198],"language":[38,199,238,242],"models":[39],"(by":[40],"using":[41,70],"headlines":[42],"articles).":[45],"The":[46,59,103,124,140,169],"creation":[47],"process":[48],"and":[49,135,230],"scripts":[50],"replication/extension":[52],"are":[53,136,297,317],"located":[54],"GitHub":[57],"repository.":[58],"has":[61,171],"been":[62],"further":[63],"extended":[64],"v2":[66,104],"obfuscated":[68,160,273,291,315,335],"10":[71],"authorship":[72],"obfuscation":[73],"methods,":[74],"EMNL":[78],"2024":[79],"Findings":[80],"If":[83],"you":[84],"use":[85],"this":[86,348],"any":[89,95],"publication,":[90],"project,":[91],"tool":[92],"or":[93,205,219],"other":[96,125],"form,":[97],"please,":[98],"cite":[99],"Files":[102],"multiple":[110],"files.":[111],"'multitude.csv'":[112],"contains":[113,127,143],"original":[114,178,279],"v1":[115],"(i.e.,":[119,276,332],"without":[120],"field":[122,131,148,152,296],"'generated').":[123],"files":[126,157],"also":[128,318],"'generated'":[130,151,270,295],"(as":[132],"below)":[134],"compressed":[137],"GZIP.":[139],"file":[141],"'multitude_obfuscated_original.csv.gz'":[142],"copies":[144],"'text'":[147,175,303],"to":[153,310],"be":[154,326,340],"compatible":[155],"with":[156,158],"(used":[162],"as":[163,300,342,344],"such":[164],"experiments).":[167],"Fields":[168],"following":[173],"fields:":[174],"-":[176,183,193,214,234,248,256,271,359,362,367,370,375,378,381,384,387,390,393,396,399,404,411,418,425,430,435,440,445,450,455,460],"an":[177,272],"(unobfuscated)":[179],"sample,":[181],"'label'":[182],"0":[184,366],"text,":[187,191,212,246,254,269],"1":[188,369],"'multi_label'":[192],"string":[195,207,216,258],"representing":[196,209],"model":[200],"that":[201],"\"human\"":[208],"'split'":[213],"identifying":[217,240,259],"train":[218,358],"test":[220,361],"split":[221],"purpose":[227],"training":[229],"evaluation":[231],"respectively,":[232],"'language'":[233],"ISO":[236],"639-1":[237],"code":[239],"given":[245,253,268],"'length'":[247],"word":[249],"count":[250],"'source'":[255],"source":[261],"/":[263],"medium":[265],"sample":[275],"transformed":[277],"obfuscator":[283,309],"indicated":[284],"corresponding":[287],"filename)":[288],"Note:":[289],"some":[290],"same":[299],"field,":[304],"indicating":[305],"failure":[306],"modify":[311],"text.":[313],"Human-written":[314],"included;":[319],"however,":[320],"labels":[321],"their":[323],"originals":[324],"might":[325],"no":[327],"longer":[328],"relevant":[329],"them":[331],"machine":[338],"could":[339],"considered":[341],"well);":[345],"thus,":[346],"consider":[347],"your":[350],"research.":[351],"Statistics":[352],"(the":[353],"number":[354],"samples)":[356],"Splits:":[357],"44786":[360],"29295":[363],"Binary":[364],"labels:":[365,373],"Multiclass":[372],"gpt-3.5-turbo":[374],"8300":[376,379],"gpt-4":[377],"text-davinci-003":[380],"8297":[382],"alpaca-lora-30b":[383],"8290":[385],"vicuna-13b":[386],"8287":[388],"opt-66b":[389],"8229":[391,394],"llama-65b":[392],"opt-iml-max-1.3b":[395],"8157":[397],"human":[398],"Languages:":[401],"English":[402],"(en)":[403],"29460":[405],"(train":[406,413,420],"+":[407,414,421],"test)":[408,415,422],"Spanish":[409],"(es)":[410],"11586":[412],"Russian":[416],"(ru)":[417],"11578":[419],"Dutch":[423],"(nl)":[424],"2695":[426],"(test)":[427,432,437,442,447,452,457,462],"Catalan":[428],"(ca)":[429],"2691":[431],"Czech":[433],"(cs)":[434],"2689":[436],"German":[438],"(de)":[439],"2685":[441],"Chinese":[443],"(zh)":[444],"2683":[446],"Portuguese":[448],"(pt)":[449],"2673":[451,456],"Arabic":[453],"(ar)":[454],"Ukrainian":[458],"(uk)":[459],"2668":[461]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
