{"status":"OK","data":{"id":579103,"identifier":"XAJ12C","persistentUrl":"https://doi.org/10.34894/XAJ12C","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2026-01-20","storageIdentifier":"surf://10.34894/XAJ12C","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9976,"datasetType":"dataset","locks":[],"latestVersion":{"id":34173,"datasetId":579103,"datasetPersistentId":"doi:10.34894/XAJ12C","datasetType":"dataset","storageIdentifier":"surf://10.34894/XAJ12C","versionNumber":3,"internalVersionNumber":21,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2026-03-20T10:37:16Z","releaseTime":"2026-03-20T10:37:16Z","createTime":"2026-03-17T15:33:46Z","publicationDate":"2026-01-20","citationDate":"2026-01-20","versionNote":"Added two additional segmentation's made by Kay Pepping (1388 and 1529). Added Kay Pepping as a contributor.","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9976,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://i.creativecommons.org/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"GLOBALISE - VOC Document Segmentation Dataset"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Smit, Renate"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Huygens Institute"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0005-1070-636X"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Pepping, Kay"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/04x6kq749","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0002-3747-706X"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"IISH Data-department"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"International Institute for Social History"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This dataset contains detailed annotations of Dutch East India Company (VOC) archival documents based on the TANAP (Towards a New Age of Partnership) project. The dataset provides precise boundaries and classifications for documents within digitized archival volumes, serving as training data for machine learning approaches to historical document segmentation and classification. This work supports the broader goal of making VOC archives more accessible beyond traditional finding aids that often reflect colonial perspectives."}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities"]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"archive"},"topicClassVocab":{"typeName":"topicClassVocab","multiple":false,"typeClass":"primitive","value":"WikiData"},"topicClassVocabURI":{"typeName":"topicClassVocabURI","multiple":false,"typeClass":"primitive","value":"https://www.wikidata.org/wiki/Q166118"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Dutch East India Company"},"topicClassVocab":{"typeName":"topicClassVocab","multiple":false,"typeClass":"primitive","value":"WikiData"},"topicClassVocabURI":{"typeName":"topicClassVocabURI","multiple":false,"typeClass":"primitive","value":"https://www.wikidata.org/wiki/Q159766"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Schnober, C., Smit, R., Kuruppath, M., Pepping, K., van Wissen, L., & Petram, L. (2024). Page Embeddings: Extracting and Classifying Historical Documents with Generic Vector Representations. In Proceedings of the Computational Humanities Research Conference 2024: Aarhus, Denmark, December 4-6, 2024 (Vol. 3834, pp. 999-1011). (CEUR Workshop Proceedings). https://ceur-ws.org/Vol-3834/paper73.pdf"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://ceur-ws.org/Vol-3834/paper73.pdf"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"This dataset was migrated from the IISH Data Collection to DataverseNL in January 2026. It was previously published as: Smit, Renate, 2026, \"GLOBALISE - VOC Document Segmentation Dataset\", https://hdl.handle.net/10622/XMCZLZ, IISH Data Collection, V1 under the persistent identifier hdl:10622/XMCZLZ."},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Pepping, Kay"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2025-09-01"}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/XAJ12C"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"3.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:ac594f1f-7458-42cc-9023-6e131fa4e46a"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-bdb3a411-5a4a-405c-b446-05f525fcc467"}]}},"files":[{"description":"","label":"1120 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579104,"persistentId":"","filename":"1120 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":35875,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36433-8f8868c8e03b","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"622f328869ca20f0bf315c03f078c87b735a3d85"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"1267 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579105,"persistentId":"","filename":"1267 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":52653,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa365b1-ed4be8be9385","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"9eca9b2b4a864069d9e526988960497e12513397"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"1274 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579106,"persistentId":"","filename":"1274 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":68669,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa366bb-f07b13298bab","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"365d9d74f878fa78cac463909453cd97ec088bc0"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"label":"1388 - Document Segmentation.csv","restricted":false,"version":1,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":615247,"persistentId":"","filename":"1388 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":43310,"categories":["Data"],"storageIdentifier":"surf://store:19d0ad055a6-fe7b773adea8","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"87df8a3d6d07e5d8e49266455cf8dd5e975d7c64"},"tabularData":false,"creationDate":"2026-03-20","publicationDate":"2026-03-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"label":"1529 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":615246,"persistentId":"","filename":"1529 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":43492,"categories":["Data"],"storageIdentifier":"surf://store:19d0acee442-8299f6f995c7","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"60224d0999f81225e3679bac4c13a634ac8e368b"},"tabularData":false,"creationDate":"2026-03-20","publicationDate":"2026-03-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"1539 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579107,"persistentId":"","filename":"1539 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":55376,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa367f7-d27acc6c4180","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"5ed9113e957e739d61ad2c4ba7814009d1823bfd"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"1547 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579108,"persistentId":"","filename":"1547 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":26564,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36903-ace819d7d97b","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"20799f6fbfed1672036497c8bb9c0fa9c9ec1fbb"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"1557 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579109,"persistentId":"","filename":"1557 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":66223,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36a26-42307f7028ce","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"a7eb743197487d9a6798f064582c0f6bbccf8a33"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"2448 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579110,"persistentId":"","filename":"2448 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":98079,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36b4d-8f36e6599fd4","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"9e91f70c0c5aa8f39c88b52ddb046386d7a5fcfb"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"2548 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579111,"persistentId":"","filename":"2548 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":97981,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36c70-58780a993e89","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"365f26e30feaaa271577d8d8ebe3ecce6a81d7d7"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"2555 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579112,"persistentId":"","filename":"2555 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":43579,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36d93-d0245b50fca2","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"ed9acdf2c9e967792e8b7fa9092491db73988a43"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"2775 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579113,"persistentId":"","filename":"2775 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":27085,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36e9d-cb5de2523662","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"85e7364afdca4225c5088cf72c716f63ac64202f"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"3142 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579114,"persistentId":"","filename":"3142 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":29862,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa36ff3-6f7b62b12a04","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"ad521433b7dcc08b50d370b36eab5803fa628608"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"3891 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579115,"persistentId":"","filename":"3891 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":33184,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa3717b-63bbf0e92364","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"a62f93e5382353d2a7763255d1c5b28ad29bd013"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"7923 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579116,"persistentId":"","filename":"7923 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":6814,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37268-d956de4ad8da","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"f3cc0221bccb2c0e492b0bef569e6defe76d9367"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8023 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579117,"persistentId":"","filename":"8023 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":5918,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37500-8c7c0e960718","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8a8d6d8d5f90b001d72a0042d60516574bdb0309"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8121 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579118,"persistentId":"","filename":"8121 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":28227,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa375ff-fea9ac33dd6d","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"0cad22bddc711cc0cb05f03067bcd2e6cd855518"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8237 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579119,"persistentId":"","filename":"8237 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":8205,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37882-fbdc859f2fb2","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"668ab34a02ff223fc3ad4f8ce2c18ed63276320e"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8276 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579120,"persistentId":"","filename":"8276 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":6987,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa379d5-56d802933c55","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"7b1833835815a592803e25c32be6f6824a7d6722"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8284 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579121,"persistentId":"","filename":"8284 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":8778,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37baf-e06483ba37f0","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"df397bb2ac74aefbbe3135542776533abb365b8b"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8697 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579122,"persistentId":"","filename":"8697 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":9515,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37c99-515b18dbdb6e","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"90786367b89e1d322ca9437229eeaa2cf0b0fbc6"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"description":"","label":"8834 - Document Segmentation.csv","restricted":false,"version":2,"datasetVersionId":34173,"categories":["Data"],"dataFile":{"id":579123,"persistentId":"","filename":"8834 - Document Segmentation.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":25516,"description":"","categories":["Data"],"storageIdentifier":"surf://store:19bdaa37f57-e1fe173fc1cb","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"41f7230f2e32cf48fcd50d5eca60ea7dbc02f2e9"},"tabularData":false,"creationDate":"2026-01-20","publicationDate":"2026-01-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}},{"label":"README - GLOBALISE - VOC Document Segmentation Dataset.pdf","restricted":false,"version":3,"datasetVersionId":34173,"categories":["Documentation"],"dataFile":{"id":615245,"persistentId":"","filename":"README - GLOBALISE - VOC Document Segmentation Dataset.pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":195041,"categories":["Documentation"],"storageIdentifier":"surf://store:19d0ac9be41-28ede5c815ba","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"5d805e0da60c0342e663cb0b3e303b1f57cb6c3f"},"tabularData":false,"creationDate":"2026-03-20","publicationDate":"2026-03-20","lastUpdateTime":"2026-03-20T10:37:16Z","fileAccessRequest":true}}]}}}