# OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Dataset

arXiv: https://arxiv.org/abs/2608.30616 · HTML: https://mlsanity.com/paper/2608.30616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 72 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [DocILE Benchmark for Document Information Localization and Extraction](https://mlsanity.com/paper/2302.05658/) (2023)
- [olmOCR 2: Unit Test Rewards for Document OCR](https://mlsanity.com/paper/2510.19817/) (2025)
- [LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR](https://mlsanity.com/paper/2601.14251/) (2026)
- [Handwritten Text Recognition: A Survey](https://mlsanity.com/paper/2502.08417/) (2025)
- [Benchmarking Large Language Models for Handwritten Text Recognition](https://mlsanity.com/paper/2503.15195/) (2025)
- [The Few-shot Dilemma: Over-prompting Large Language Models](https://mlsanity.com/paper/2509.13196/) (2025)
- [Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review](https://mlsanity.com/paper/2408.06345/) (2024)
- [Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition](https://mlsanity.com/paper/2302.06308/) (2023)
- [VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents](https://mlsanity.com/paper/2603.15118/) (2026)
- [PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation](https://mlsanity.com/paper/2412.11574/) (2024)
- [PyPotteryInk: One-Step Diffusion Model for Sketch to Publication-ready Archaeological Drawings](https://mlsanity.com/paper/2502.06897/) (2025)
- [CM1 -- A Dataset for Evaluating Few-Shot Information Extraction with Large Vision Language Models](https://mlsanity.com/paper/2505.04214/) (2025)
- [Machine learning applications in archaeological practices: a review](https://mlsanity.com/paper/2501.03840/) (2025)
- [The Character Error Vector: Decomposable errors for page-level OCR evaluation](https://mlsanity.com/paper/2604.06160/) (2026)
- [ArchiveGPT: A human-centered evaluation of using a vision language model for image cataloguing](https://mlsanity.com/paper/2507.07551/) (2025)

## Abstract (arXiv)

Pottery is a primary source for reconstructing the chronological and economic dimensions of past societies. Archaeologists often document ceramic finds through technical drawings and handwritten metadata. This metadata is critical for dating, provenance attribution, and cross-site comparison, but remains inaccessible to computational analysis, requiring manual transcription of every record. We investigate whether state-of-the-art document analysis models can address this task, and introduce CENTURIA, a dataset of 507 pottery records from the Roman site of Carnuntum, providing transcriptions, bounding boxes, and structured field-level labels across seven metadata categories. Benchmarking five OCR models reveals a substantial domain gap: zero-shot transcription error reaches 15-32% SpACER-M, far exceeding rates on printed archival documents, with domain-specific fields recovered in fewer than 3% of cases. LoRA fine-tuning on just 57 samples, reflecting a realistic archival annotation budget, closes this gap, reducing transcription error to below 1.5% and recovering overall field-level accuracy above 87%. Our results show that a small expert-validated fine-tuning set suffices to convert handwritten pottery documentation into structured, searchable metadata ready for archaeological databases.