Introduces a benchmark dataset for data snapshot extraction focused on semantically meaningful analytical artifacts in institutional documents and shows open-source layout models struggle to generalize from academic benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Open-Source Layout Detection Models for Data Snapshot Extraction from Institutional Documents
Introduces a benchmark dataset for data snapshot extraction focused on semantically meaningful analytical artifacts in institutional documents and shows open-source layout models struggle to generalize from academic benchmarks.