Who used what
Tools and datasets in the centre, projects around the edge. Click any point to see its connections. Turn benchmarks off to see which tools historians have actually put to work.
75 of 75 projects shown · 52 research or corpus, 23 evaluations
Drag to move around. Zoom with the buttons, Ctrl/⌘ + scroll, or pinch with two fingers.
Show the connections as a list
The same information as the graph, for screen readers and small screens. Evaluations are included.
ABBYY FineReader PDF
Evaluation: Digitization Decisions: comparing OCR software (2021); Newspaper OCR quality: What Have We Learned? (2020); Enhanced OCR for mass digitisation (2018)
Canadiana
Research: Coal and place text-mined from Early Canadiana Online (2013)
Corpus building: Indian Affairs letterbooks transcribed with HTR (2024); A historical commodities lexicon (Trading Consequences) (2014)
Evaluation: Rating OCR quality in Early Canadiana Online (2014)
Chandra
Evaluation: Reading the Archive by Machine: An OCR Benchmark for Historians (2026); When Low CER is Not Enough (2026)
Chronicling America
Research: America’s Public Bible (2023); Uncovering reprinted texts in antebellum newspapers (Viral Texts) (2015)
Corpus building: American Stories: structured text of US newspapers (2023)
Evaluation: ChroniclingAmericaQA (2024)
DeepSeek-OCR
Evaluation: Reading or Guessing? VLM OCR on Greek and Arabic editions (2026); socOCRbench (2026); When Low CER is Not Enough (2026)
eScriptorium
Corpus building: Reading manuscripts with HTR (2026); BiblIA: medieval Hebrew manuscripts (2021)
Evaluation: A 13th-century French cartulary in eScriptorium (2024)
Gephi
Research: Finnish literary translation circles (2026); Sociability in scientific expeditions (2021); Visualising the Republic of Letters catalogue (2011)
HathiTrust
Research: The gender agency gap in fiction writing, 1850–2010 (2024); Feminist Bestsellers: A Digital History of 1970s Feminism (2021)
Corpus building: NovelTM datasets for English-language fiction (2020)
Evaluation: Cleaning Dirty Books: post-OCR processing (2021)
Kraken
Corpus building: BiblIA: medieval Hebrew manuscripts (2021); Tikkoun Sofrim: Hebrew manuscripts with volunteers (2019)
Evaluation: Reading or Guessing? VLM OCR on Greek and Arabic editions (2026); Arabographic OCR (OpenITI) (2017)
MALLET
Research: The Many Themes of Humanism in the German press (2020); Mining the Dispatch (c. 2010–2012); Topic Modeling Martha Ballard’s Diary (2010)
Mistral OCR
Corpus building: Dictionnaire de Trévoux (1743) OCR pipeline (2026); OCR pipeline for historical print periodicals (2025–2026)
Evaluation: socOCRbench (2026)
Old Bailey Online
Research: Text Mining the Old Bailey for Evidence of Court Behavior (2016); The civilizing process in London’s Old Bailey (2014)
Corpus building: Old Bailey Corpus 2.0 (2016)
Evaluation: Benchmarking cloud OCR on 180,000 Old Bailey pages (2020)
olmOCR
Evaluation: The Invisibility of Historical Documents in OCR evaluation (2026); Reading or Guessing? VLM OCR on Greek and Arabic editions (2026); Reading the Archive by Machine: An OCR Benchmark for Historians (2026); socOCRbench (2026); OCR for Pre-Digital Historical Documents using LLMs (2025)
PaddleOCR-VL
Corpus building: Digitizing 20 million historical census documents (2026)
Evaluation: socOCRbench (2026)
QGIS
Research: Gender, discrimination and housing in Montréal, 1901–03 (2016)
Corpus building: Historical Atlas of the Low Countries, 1350–1800 (2023); Montréal, l’avenir du passé (MAP) (2000–)
Recogito
Research: Burchard of Mount Sion’s Descriptio terrae sanctae (2021)
Corpus building: Digital Periegesis (Pausanias) (2017–); Pelagios 3: early geospatial documents (2015)
Evaluation: Discovering Object Stories (Recogito Studio) (2025)
SlaveVoyages
Research: Atlantic History and the Slave Trade to Spanish America (2015); Ship crowding and slave mortality (2014)
Corpus building: Enslaved.org: Peoples of the Historical Slave Trade (2020)
spaCy
Corpus building: Geoparsing the Gazetteers of Scotland (2020)
Evaluation: NER for the multilingual Persian Gulf (2022); Ensemble NER for historical place names (2018)
StoryMap JS
Research: Telling a tale of World War I with StoryMap (2018); March on Milwaukee digital curation (n.d.)
Corpus building: Relaciones Geográficas maps (2018)
Tesseract
Corpus building: Deutscher Reichsanzeiger, 1819–1945 (2018–2019); Ontario newspapers on a shoestring (2017)
Evaluation: The Invisibility of Historical Documents in OCR evaluation (2026); Reading or Guessing? VLM OCR on Greek and Arabic editions (2026); Reading the Archive by Machine: An OCR Benchmark for Historians (2026); Digitization Decisions: comparing OCR software (2021); OCR quality and newspaper clippings (c. 2021); Enhanced OCR for mass digitisation (2018)
Transkribus
Corpus building: Indian Affairs letterbooks transcribed with HTR (2024); VOC, WIC and notarial deeds: 2 million pages (2020)
Evaluation: Transcribing the Ottoman Turkish print archive (c. 2020); HTR and Sloane’s Miscellanies catalogue (2019)
Trove newspapers
Research: Domestic workers of colour in late 19th-century Australia (2020); A World of Fiction: Digital Collections and the Future of Literary History (2018)
Corpus building: To be continued: fiction in Australian newspapers (2019); Finding Names in Trove (2015)
Voyant Tools
Research: Palabras de fidelidad: Bishop González del Campillo’s letters (2026); The repression of banditry in Andalusia (2023); Textile making in the Lienü zhuan (2021)
Whisper
Corpus building: Captioning archival audiovisual collections (2023)
Evaluation: Whisper on the Fortunoff Holocaust testimonies (2026); Whisper and Portuguese oral history (2026)
World Historical Gazetteer
Corpus building: Belgian Historical Gazetteer (2026); EMEW: a gazetteer of early modern England and Wales (2024); Dutch Global History datasets (2022); HGIS de las Indias in WHG (2022)