{"id":"https://openalex.org/W6949672156","doi":"https://doi.org/10.5281/zenodo.15538126","title":"The Million Authors Corpus (MAC)","display_name":"The Million Authors Corpus (MAC)","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W6949672156","doi":"https://doi.org/10.5281/zenodo.15538126"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15538126","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15538126","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.15538126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"May, Jonathan","orcid":"https://orcid.org/0000-0002-5284-477X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"May, Jonathan","raw_affiliation_strings":["University of Southern California"],"raw_orcid":"https://orcid.org/0000-0002-5284-477X","affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jurgens, David","orcid":"https://orcid.org/0000-0002-2135-9878"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jurgens, David","raw_affiliation_strings":["University of Michigan\u2013Ann Arbor"],"raw_orcid":"https://orcid.org/0000-0002-2135-9878","affiliations":[{"raw_affiliation_string":"University of Michigan\u2013Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liu, Shuai","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Shuai","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/style","display_name":"Style (visual arts)","score":0.454800009727478},{"id":"https://openalex.org/keywords/lexicography","display_name":"Lexicography","score":0.4187000095844269},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3896999955177307},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.35899999737739563},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.3391999900341034},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.3093000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724000215530396},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C80976798","wikidata":"https://www.wikidata.org/wiki/Q184524","display_name":"Lexicography","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.3093000054359436},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C53605480","wikidata":"https://www.wikidata.org/wiki/Q852595","display_name":"Geotagging","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15538126","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15538126","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.15538126","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15538126","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":{"We":[0,153],"introduce":[1],"the":[2,57,81,87,94,106,111,114,121,148,158,191,196],"Million":[3],"Authors":[4],"Corpus":[5],"(MAC),":[6],"a":[7,51,62,137,143,155],"novel":[8],"dataset":[9],"encompassing":[10],"contributions":[11],"from":[12,27,147],"dozens":[13],"of":[14,93,120,157],"languages":[15],"on":[16],"Wikipedia.":[17],"It":[18],"includes":[19,61],"only":[20],"long":[21],"and":[22,30,101,128],"contiguous":[23],"textual":[24],"chunks":[25],"taken":[26,146],"Wikipedia":[28,67,115],"edits":[29],"links":[31],"those":[32],"texts":[33],"to":[34,113],"their":[35],"authors.":[36],"The":[37,103],"zipped":[38,77],"file":[39,53,60,89],"contains":[40,75],"60":[41],"directories,":[42],"one":[43],"per":[44,65,163],"language.":[45],"Within":[46],"each":[47,66,73],"directory,":[48],"we":[49,69],"share":[50],"csv":[52],"with":[54,80],"meta-information":[55],"about":[56],"content.":[58,83],"This":[59],"row-level":[63],"data":[64],"page":[68,169],"process.":[70],"In":[71],"addition,":[72],"folder":[74],"multiple":[76],"jsonl":[78,88],"files":[79],"raw-level":[82],"Each":[84],"raw":[85],"in":[86,136],"holds":[90],"12":[91],"fields":[92],"records":[95],"such":[96],"as":[97,193],"id,":[98],"timestamp,":[99],"page,":[100],"new_text.":[102],"latter":[104],"is":[105,195],"new":[107],"text":[108],"added":[109],"by":[110,200],"user":[112,168],"page.":[116],"A":[117],"concise":[118],"version":[119],"dataset,":[122],"which":[123],"was":[124],"used":[125],"for":[126],"training":[127],"testing":[129],"out":[130],"proposed":[131],"algorithms":[132],"can":[133],"be":[134,190],"found":[135],"HuggingFace":[138],"repository:":[139],"https://huggingface.co/datasets/Blablablab/MAC":[140],"Here":[141],"are":[142,161],"few":[144],"examples,":[145],"South":[149],"African":[150],"language":[151],"('za').":[152],"show":[154],"subset":[156],"keys":[159],"that":[160],"included":[162],"instance":[164],":":[165],"id":[166],"timestamp":[167],"sha1":[170],"new_text":[171],"99223":[172],"2023-01-25T13:12:48Z":[173],"{'id':":[174,178,206,211,237],"18564,":[175],"'text':":[176,208],"'Laasry'}":[177],"607,":[179],"'title':":[180,213,239],"'Ikhasi":[181],"Elikhulu',":[182],"'namespace':":[183,217,241],"1,":[184],"'restrictions':":[185,219,243],"[]}":[186,220,244],"bww0jvlrrfvemlf0x5zxx7rkzh0n8jm":[187],"[\\':\"uNomaxhama\"":[188],"should":[189],"format":[192],"it":[194],"capitalisation":[197],"style":[198],"adopted":[199],"lexicography":[201],"units":[202],"and...]":[203],"11315":[204],"2009-01-20T13:43:23Z":[205],"88,":[207],"'Andre":[209],"Engels'}":[210],"794,":[212],"'Uphiko":[214],"Lwezilimi":[215],"Kuzwelonke',":[216],"0,":[218,242],"80fh22mjubxw556yhbzsr4et3wgpi8f":[221],"['Uphiko":[222],"lweziLimi":[223],"kuZweIonke":[224],"(NLS)":[225],"lugqugquzela":[226],"futhi":[227],"lwenza":[228],"lula":[229],"ukuxoxisana":[230],"ngezilimi":[231],"ezahlukene\\...]":[232],"65078":[233],"2020-08-31T20:55:00Z":[234],"{'text':":[235],"'197.77.175.185'}":[236],"1031,":[238],"'IsiZulu',":[240],"ep8r9ii1jri1zjjpfvj46zpwtdyio2d":[245],"['Lolu":[246],"limi":[247],"lusukela":[248],"noma":[249,259],"luqanjwe":[250],"ngowayeyiSilo":[251],"samabandla":[252],"onke":[253],"iNkosi":[254],"uShaka":[255],"Zulu\\\\nLokhu":[256],"kungenxa":[257],"yegalelo":[258],"iqhaza":[260],"alibamba":[261],"ekubumbeni":[262],"isizwe":[263],"esasihlukene...]":[264]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
