# Quantifying and extending the coverage of spatial categorization data sets Source: [Quantifying and extending the coverage of spatial categorization data sets]() Collection index: [llms.txt]() Data updated: 2026-03-12T05:00:04.726Z Authors: Wanchun Li, Alexandra Carstensen, Yang Xu, Terry Regier, Charles Kemp Published: 2026-03-10T08:49:11.000Z ## Abstract Variation in spatial categorization across languages is often studied by eliciting human labels for the relations depicted in a set of scenes known as the Topological Relations Picture Series (TRPS). We demonstrate that labels generated by large language models (LLMs) align relatively well with human labels, and show how LLM-generated labels can help to decide which scenes and languages to add to existing spatial data sets. To illustrate our approach we extend the TRPS by adding 42 new scenes, and show that this extension achieves better coverage of the space of possible scenes than two previous extensions of the TRPS. Our results provide a foundation for scaling towards spatial data sets with dozens of languages and hundreds of scenes. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Spatial relation coverage analysis on Universe of 220 spatial scenes 1.0 (Stimulus set coverage)](): Spatial relation coverage analysis; Universe of 220 spatial scenes 1.0 (Stimulus set coverage); Coverage Score: 96.4. ## Original sources and implementation [Original paper]() [PDF]()