# Benchmarking Open-Source Layout Detection Models for Data Snapshot Extraction from Institutional Documents

arXiv: https://arxiv.org/abs/2606.06242 · HTML: https://mlsanity.com/paper/2606.06242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [TableBank: A Benchmark Dataset for Table Detection and Recognition](https://mlsanity.com/paper/1903.01949/) (2019)
- [LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding](https://mlsanity.com/paper/2404.05225/) (2024)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [Vision Grid Transformer for Document Layout Analysis](https://mlsanity.com/paper/2308.14978/) (2023)
- [Quantitative Information Extraction from Humanitarian Documents](https://mlsanity.com/paper/2408.04941/) (2024)
- [LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis](https://mlsanity.com/paper/2603.17265/) (2026)

## Abstract (arXiv)

Institutional documents contain substantial amounts of operational and analytical information embedded within figures and tables. Current approaches for extracting visual content from documents are largely built around generic document layout analysis, where figures and tables are treated as uniformly relevant document objects rather than semantically meaningful analytical artifacts. In this work, we introduce a benchmark dataset and evaluation framework for textitdata snapshot extraction, the task of identifying and localizing semantically meaningful visual artifacts within institutional documents. The benchmark spans humanitarian reports, World Bank policy research working papers, and project appraisal documents, and includes annotations for figures and tables that contain reusable analytical information. Using this dataset, we benchmarked multiple open-source layout detection models and evaluated both detection performance and spatial extraction quality. Our results show that current models struggle to generalize to operational institutional documents despite strong performance on conventional academic benchmarks. Common failure modes include confusion between analytical and non-analytical content, fragmentation of composite analytical artifacts, and incomplete extraction of contextual information required for interpretation. These findings highlight a persistent gap between generic document layout analysis and operationally useful data snapshot extraction. We release the source PDFs, annotation dataset, metadata, and source code to support future research in operational document intelligence. The dataset is available at https://huggingface.co/datasets/ai4data/data-snapshot and the source code is available at https://github.com/worldbank/ai4data/tree/main/experimental/data-snapshot.