Guides
Short, practical walkthroughs. Aimed at the working researcher, not the implementer — if you want the engineering details, see the articles.
- getting-started · tutorial · translation
Reading a book in translation
From an uploaded PDF to a book you can read page by page with its original script, a romanisation and a translation side by side, chapters and people found for you.
- export · archiving · snapshots · how-to
Exporting and archiving a dataset
A grounded walkthrough of Archēglyph's dataset snapshot: what goes into the tarball, how to open it without the product, and how to cite it in a paper.
- review · ocr · vlm · how-to
Reviewing a noisy scan
A walkthrough of the review screen on a low-quality scan: what to look for, how to read the confidence tint, and when to re-run a region with a VLM instead.
- extraction · ocr · vlm · decision
OCR vs VLM: a practical chooser
A decision-oriented guide to picking the right extraction engine: when Tesseract is the right default, when a VLM earns its cost, and how to test cheaply.
- getting-started · tutorial
Your first dataset
End-to-end walkthrough: sign in, create a dataset, upload pages, watch the pipeline run, review a document, and run your first search.
- pipeline · overview
The pipeline: upload, assess, extract, analyse
A plain-language tour of the four stages a document passes through: upload, assess, extract, and analyse — written for the person using the product.