{"id":13434959,"identifier":"DVN/M5PRZB","persistentUrl":"https://doi.org/10.7910/DVN/M5PRZB","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2026-02-04","storageIdentifier":"s3://10.7910/DVN/M5PRZB","datasetType":"dataset","datasetVersion":{"id":611677,"datasetId":13434959,"datasetPersistentId":"doi:10.7910/DVN/M5PRZB","datasetType":"dataset","storageIdentifier":"s3://10.7910/DVN/M5PRZB","versionNumber":2,"internalVersionNumber":4,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2026-02-05T03:58:01Z","releaseTime":"2026-02-05T03:58:01Z","createTime":"2026-02-05T03:57:40Z","publicationDate":"2026-02-04","citationDate":"2026-02-04","license":{"name":"CC0 1.0","uri":"http://creativecommons.org/publicdomain/zero/1.0","iconUri":"https://licensebuttons.net/p/zero/1.0/88x31.png","rightsIdentifier":"CC0-1.0","rightsIdentifierScheme":"SPDX","schemeUri":"https://spdx.org/licenses/","languageCode":"en"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Kang, Inmo"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0009-9244-6360"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Park, Joonmo"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0007-5917-5701"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Jeong, Heesoo"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0005-9592-8788"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Chung, Seyoung"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0006-0037-1065"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Jeon, Changmin"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0000-0711-1158"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Moon, Seongwuk"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-0375-533X"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Moon, Seongwuk"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Sogang University, Seoul, Korea"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"seongwuk@sogang.ac.kr"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"Dataset 1. The dataset analyzed during the current study."}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Social Sciences"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"(KCSE), Korean Councils of Science Editors"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-02-04"}]}},"files":[{"label":"20251220_SciEdit_ROR corpus_Submit.json","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13435379,"persistentId":"","filename":"20251220_SciEdit_ROR corpus_Submit.json","contentType":"application/json","friendlyType":"JSON","filesize":27951904,"storageIdentifier":"s3://dvn-cloud:19c2bf2ab60-42c405833200","rootDataFileId":-1,"md5":"1c2d5d72a7f57d200105acbbf6f45f16","checksum":{"type":"MD5","value":"1c2d5d72a7f57d200105acbbf6f45f16"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}},{"label":"Dataset 1. The dataset analyzed during the current study..csv","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13434960,"persistentId":"","filename":"Dataset 1. The dataset analyzed during the current study..csv","contentType":"text/comma-separated-values","friendlyType":"Comma Separated Values","filesize":16368830,"storageIdentifier":"s3://dvn-cloud:19c2b7e24cd-9794c6c84572","rootDataFileId":-1,"md5":"9eb6a588057ed3c3a7d25e3fdfc876fe","checksum":{"type":"MD5","value":"9eb6a588057ed3c3a7d25e3fdfc876fe"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}},{"label":"geo_data.json","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13435378,"persistentId":"","filename":"geo_data.json","contentType":"application/json","friendlyType":"JSON","filesize":10177,"storageIdentifier":"s3://dvn-cloud:19c2bf2a9b4-785429a94c3a","rootDataFileId":-1,"md5":"9b090e6a99b096bce98fdc3b2fb37cef","checksum":{"type":"MD5","value":"9b090e6a99b096bce98fdc3b2fb37cef"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}},{"label":"Suppl. 1. Methods for constructing the ROR corpus, PubMed sample, and gold standard..pdf","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13434973,"persistentId":"","filename":"Suppl. 1. Methods for constructing the ROR corpus, PubMed sample, and gold standard..pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":145280,"storageIdentifier":"s3://dvn-cloud:19c2b82a8b7-60998b43d52a","rootDataFileId":-1,"md5":"4e2604a1ab8497320e4b0ec083a57dd9","checksum":{"type":"MD5","value":"4e2604a1ab8497320e4b0ec083a57dd9"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}},{"label":"Suppl. 2. Model implementation details..pdf","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13434972,"persistentId":"","filename":"Suppl. 2. Model implementation details..pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":165417,"storageIdentifier":"s3://dvn-cloud:19c2b82a70a-0db122caee4c","rootDataFileId":-1,"md5":"4cfddb6438f9dca0447289be589b4b46","checksum":{"type":"MD5","value":"4cfddb6438f9dca0447289be589b4b46"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}},{"label":"Suppl. 3. Evaluation metrics and baseline implementation..pdf","restricted":false,"version":1,"datasetVersionId":611677,"dataFile":{"id":13434971,"persistentId":"","filename":"Suppl. 3. Evaluation metrics and baseline implementation..pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":144969,"storageIdentifier":"s3://dvn-cloud:19c2b82a56d-26e73d25b36e","rootDataFileId":-1,"md5":"db2e048a41708585454e11f7e96d4e3f","checksum":{"type":"MD5","value":"db2e048a41708585454e11f7e96d4e3f"},"tabularData":false,"creationDate":"2026-02-04","publicationDate":"2026-02-04","lastUpdateTime":"2026-02-05T03:58:01Z","fileAccessRequest":true}}],"citation":"Kang, Inmo; Park, Joonmo; Jeong, Heesoo; Chung, Seyoung; Jeon, Changmin; Moon, Seongwuk, 2026, \"A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study\", https://doi.org/10.7910/DVN/M5PRZB, Harvard Dataverse, V2"}}