SOURCE-LINKED INTELLIGENCE

Lot Machine: Multimodal Lot Extraction from Auction Catalogs

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

For provenance research and art market studies, auction catalogs are an essential resource to trace specific objects over time and space. While historical auction catalogs follow established domain conventions, their internal formatting remains highly variable, and their large-scale analysis is currently restricted by the lack of machine-readable representations of the auction lots. We propose a pipeline to automatically extract structured lot-level metadata from German Sales, a large database of historical auction and sales catalogs from the 19th and 20th centuries. Using a manually annotated

Read original source ↗ Open in workspace

recordType

paper

region

Global