persNamer 1.2: One VIAF Number, Nine Authority Files
persNamer takes a VIAF number and hands back a TEI person entry. Version 1.2 makes that entry worth having: variant names, normalised dates, the identifiers of nine national and …
tei-mcp v0.3: Encoding TEI Without Rewriting the Source
tei-mcp v0.3 introduces span-locked composition, which makes the most damaging hallucination in AI-assisted TEI encoding impossible: silent rewrites of the source. The model never …
A Different Kind of Digital Edition
Most primary sources never get published. The grant-funded digital edition model is too expensive, too centralised, and too fragile to work at scale. Here's why I'm building the …
tei-mcp: TEI P5 for AI Agents
tei-mcp is an open-source MCP server that gives AI coding assistants direct access to the TEI P5 specification — element lookup, attribute resolution, nesting validation, …
Multi-Saxon
A high-performance tool for parallel XSLT 2.0/3.0 transformations of large XML TEI corpora, handling transformations that LXML cannot process.
•
1 min read
Large-scale Bibliographic Parsing with Pre-Trained Language Models
GPT-3 helps converting large amounts of bibliography into a database in a short amount of time
Efficient Editing
A series of blog posts where I evaluate different approaches to drive the cost of scholarly editions down
•
1 min read
Avviso | Publishing the News that Made us Modern (1537—1743)
An NEH-funded Medici Archive Project
•
1 min read