# The Devil is in the Details -- From OCR for Old Church Slavonic to Purely Visual Stemma Reconstruction

arXiv: https://arxiv.org/abs/2604.11724 · HTML: https://mlsanity.com/paper/2604.11724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents](https://mlsanity.com/paper/2504.00414/) (2025)
- [OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches](https://mlsanity.com/paper/2502.01205/) (2025)
- [Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities](https://mlsanity.com/paper/2510.06743/) (2025)
- [Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI](https://mlsanity.com/paper/2310.09091/) (2023)

## Abstract (arXiv)

The age of artificial intelligence has brought many new possibilities and pitfalls in many fields and tasks. The devil is in the details, and those come to the fore when building new pipelines and executing small practical experiments. OCR and stemmatology are no exception. The current investigation starts comparing a range of OCR-systems, from classical over machine learning to LLMs, for roughly 6,000 characters of late handwritten church slavonic manuscripts from the 18th century. Focussing on basic letter correctness, more than 10 CS OCR-systems among which 2 LLMs (GPT5 and Gemini3-flash) are being compared. Then, post-processing via LLMs is assessed and finally, different agentic OCR architectures (specialized post-processing agents, an agentic pipeline and RAG) are tested. With new technology elaborated, experiments suggest, church slavonic CER for basic letters may reach as low as 2-3% but elaborated diacritics could still present a problem. How well OCR can prime stemmatology as a downstream task is the entry point to the second part of the article which introduces a new stemmatic method based solely on image processing. Here, a pipeline of automated visual glyph extraction, clustering and pairwise statistical comparison leading to a distance matrix and ultimately a stemma, is being presented and applied to two small corpora, one for the church slavonic Gospel of Mark from the 14th to 16th centuries, one for the Roman de la Rose in French from the 14th and 15th centuries. Basic functioning of the method can be demonstrated.