Skip to content
When to Use OCR confidence scores

When to use OCR confidence scores and when not to: the trade-offs, costs and signals that tell you whether this approach fits your sources and project before

How to Share executable notebooks

A step-by-step guide on how to share executable notebooks, with practical defaults, settings and the pitfalls to avoid so you reach a usable result on your own

Best Practices to Record provenance metadata

Best practices and a working checklist to record provenance metadata, so your results stay consistent, documented and defensible across a whole collection

Link TEI transcriptions to IIIF: A Practical Guide

A practical guide to link TEI transcriptions to IIIF for working historians and archivists, covering the workflow end to end with concrete examples you can

Add discovery metadata to datasets: A Practical Guide

A practical guide to add discovery metadata to datasets for working historians and archivists, covering the workflow end to end with concrete examples you can copy.

Beginner's Guide to Wikidata lexemes for historical words

A gentle beginner's guide to use Wikidata lexemes for historical words, explaining the core ideas in plain language with a small worked example you can follow

How to Describe correspondence series

A step-by-step guide on how to describe correspondence series, with practical defaults, settings and the pitfalls to avoid so you reach a usable result on your first pass.

How to Mine text despite OCR noise

A step-by-step guide on how to mine text despite OCR noise, with practical defaults, settings and the pitfalls to avoid so you reach a usable result on your

How to Choose diplomatic vs normalised transcription

A step-by-step guide on how to choose diplomatic vs normalised transcription, with practical defaults, settings and the pitfalls to avoid so you reach a usable

Beginner's Guide to Relations between entities

A gentle beginner's guide to extract relations between entities, explaining the core ideas in plain language with a small worked example you can follow from a