{"id":"https://openalex.org/W7129008978","doi":"https://doi.org/10.5281/zenodo.18663775","title":"COMET arXiv preprint author affiliation extraction and ROR ID matching results","display_name":"COMET arXiv preprint author affiliation extraction and ROR ID matching results","publication_year":2025,"publication_date":"2025-02-16","ids":{"openalex":"https://openalex.org/W7129008978","doi":"https://doi.org/10.5281/zenodo.18663775"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.18663775","doi":"https://doi.org/10.5281/zenodo.18663775","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18663775","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18663775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009871346","display_name":"Parth Sarin","orcid":"https://orcid.org/0009-0004-9317-1446","observed_orcids":["https://orcid.org/0009-0004-9317-1446"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"sarin, parth","raw_affiliation_strings":["Stanford University"],"raw_orcid":"https://orcid.org/0009-0004-9317-1446","affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106435263","display_name":"Adam Buttrick","orcid":"https://orcid.org/0000-0003-1507-1031","observed_orcids":["https://orcid.org/0000-0003-1507-1031"]},"institutions":[{"id":"https://openalex.org/I2801248553","display_name":"California Digital Library","ror":"https://ror.org/03yrm5c26","country_code":"US","type":"archive","lineage":["https://openalex.org/I2801248553","https://openalex.org/I4387154595"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buttrick, Adam","raw_affiliation_strings":["California Digital Library","Research Organization Registry"],"raw_orcid":"https://orcid.org/0000-0003-1507-1031","affiliations":[{"raw_affiliation_string":"California Digital Library","institution_ids":["https://openalex.org/I2801248553"]},{"raw_affiliation_string":"Research Organization Registry","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":false,"primary_topic":{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.5473999977111816,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.5473999977111816,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.2705000042915344,"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/T14320","display_name":"Optics and Image Analysis","score":0.029999999329447746,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/research-organization-registry","display_name":"Research Organization Registry","score":0.6899999976158142},{"id":"https://openalex.org/keywords/qwen3-8b","display_name":"Qwen3-8B","score":0.6729999780654907},{"id":"https://openalex.org/keywords/research-organization-identifiers","display_name":"research organization identifiers","score":0.5580000281333923},{"id":"https://openalex.org/keywords/bibliographic-metadata","display_name":"bibliographic metadata","score":0.47099998593330383},{"id":"https://openalex.org/keywords/pdf-text-extraction","display_name":"PDF text extraction","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7523000240325928},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6732000112533569},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6610000133514404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489999890327454},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C43169469","wikidata":"https://www.wikidata.org/wiki/Q580922","display_name":"Preprint","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C2780277889","wikidata":"https://www.wikidata.org/wiki/Q282301","display_name":"Demonstrative","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.18663775","doi":"https://doi.org/10.5281/zenodo.18663775","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18663775","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.18663776","doi":"https://doi.org/10.5281/zenodo.18663776","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18663776","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18663775","doi":"https://doi.org/10.5281/zenodo.18663775","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18663775","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F1906933958","display_name":"The Navigation Fund","ror":"https://ror.org/00mgfk810"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6949909395","https://openalex.org/W7172303651","https://openalex.org/W6922272147","https://openalex.org/W4393735424","https://openalex.org/W4393520745","https://openalex.org/W7127960208","https://openalex.org/W7155213335","https://openalex.org/W19799978","https://openalex.org/W6958612718","https://openalex.org/W7144786945"],"abstract_inverted_index":{"#":[0],"arXiv":[1,12,30,76,157,169,179],"Author":[2,195],"Affiliations":[3],"This":[4,24],"dataset":[5,25,71],"contains":[6,72],"author":[7,45],"affiliation":[8,207,213],"data":[9],"extracted":[10,49,53,198],"from":[11,28,168,178,199],"works,":[13],"matched":[14,56,88],"to":[15,40,57,89],"Research":[16],"Organization":[17],"Registry":[18],"(ROR)":[19],"identifiers.":[20,91],"##":[21,106],"Dataset":[22],"Description":[23,153],"was":[26],"generated":[27],"all":[29],"works":[31,94],"as":[32,197],"of":[33,83,103,137,187,206],"2025/12.":[34],"The":[35,52,70],"source":[36],"PDFs":[37],"were":[38,47,55,86,95],"converted":[39],"markdown":[41],"using":[42,50,60],"[markitdown](https://github.com/microsoft/markitdown),":[43],"and":[44],"affiliations":[46,54,191],"then":[48],"[cometadata/affiliation-parsing-lora-Qwen3-8B-distil-GLM_4.5_Air](https://huggingface.co/cometadata/affiliation-parsing-lora-Qwen3-8B-distil-GLM_4.5_Air).":[51],"ROR":[58,68,90,218],"IDs":[59],"the":[61,67,100,104,116,200],"[single":[62],"search":[63],"matching":[64],"strategy](https://doi.org/10.71938/zz90-g810)":[65],"in":[66],"API.":[69],"approximately":[73],"2.8":[74],"million":[75,80],"papers":[77],"with":[78,115,159,189],"12.1":[79],"author-affiliation":[81],"pairs,":[82],"which":[84],"75.8%":[85],"successfully":[87],"Approximately":[92],"10,000":[93],"excluded":[96],"because":[97],"they":[98],"exceeded":[99],"context":[101],"size":[102],"model.":[105],"Data":[107],"Format":[108],"Each":[109],"line":[110],"is":[111],"a":[112],"JSON":[113],"object":[114],"following":[117],"structure:":[118],"```json{":[119],"\"arxiv_id\":":[120],"\"arXiv:1109.3791\",":[121],"\"doi\":":[122],"\"10.48550/arxiv.1109.3791\",":[123],"\"version\":":[124],"\"v1\",":[125],"\"prediction\":":[126],"[":[127,133],"{":[128,134],"\"name\":":[129],"\"Author":[130],"Name\",":[131],"\"affiliations\":":[132],"\"affiliation\":":[135],"\"Department":[136],"Computer":[138],"Science,":[139],"Example":[140],"University\",":[141],"\"ror_id\":":[142],"\"https://ror.org/example123\"":[143],"}":[144,146],"]":[145],"]}```":[147],"###":[148],"Fields":[149],"|":[150,152,156,165,175,185,194,204,211,217,227],"Field":[151],"||-------|-------------||":[154],"`arxiv_id`":[155],"identifier":[158,219],"prefix":[160],"(e.g.,":[161,171,180],"`arXiv:1109.3791`)":[162],"||":[163,173,183,192,202,209,215],"`doi`":[164],"DOI":[166],"derived":[167],"ID":[170],"`10.48550/arxiv.1109.3791`)":[172],"`version`":[174],"Paper":[176],"version":[177],"`v1`,":[181],"`v2`)":[182],"`prediction`":[184],"Array":[186,205],"authors":[188],"their":[190],"`prediction[].name`":[193],"name":[196],"paper":[201],"`prediction[].affiliations`":[203],"objects":[208],"`prediction[].affiliations[].affiliation`":[210],"Raw":[212],"text":[214],"`prediction[].affiliations[].ror_id`":[216],"URL,":[220],"or":[221],"`null`":[222],"if":[223],"no":[224],"match":[225],"found":[226]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-17T00:00:00"}
