Pothen.

A CULTURAL ATTRIBUTION BENCHMARK

Can Vision-Language Models Tell Where a Cultural Object Comes From?

750 museum objects. Five catalogue fields. One attribution.

How much of the story can models recover?

Nine models, from individual fields to a complete attribution. Choose a metric, then select two models to compare.

Download data ↓
INDIVIDUAL FIELDS

Complete-record accuracy

All five fields compatible with the museum record.

Point estimate 95% object-bootstrap interval Pooled referenceClick a model to add it to the comparison ↓

Loading model results…

Scores are percentages of valid outputs. Each model attempted 750 objects. Overall: 6,542 valid · 208 invalid. Invalid outputs are excluded from accuracy denominators.

Whiskers: 95% object-bootstrap intervals (10,000 shared resamples). Sorting shows point estimates; overlapping intervals limit fine-grained ranking.

MODEL COMPARISON

Look beneath the overall score.

Choose any two models above, or change them here.

Each bar is a field-level compatibility rate. A higher field score does not ensure a coherent complete record. Field-specific confidence intervals are not reported in this release.

From an image to a cultural attribution.

Image-only models predict five catalogue fields—title, culture, period, origin and creator—evaluated for semantic compatibility with museum-authored references.

Pothen on film

English · 2:30

A world of objects.

Browse the benchmark’s cultural objects. Open an object to explore its museum record.

The record is
open to inquiry.

Explore the images, reference alternatives, model predictions, human annotations, judge decisions, and reproducibility code in the dataset release.

Authors & affiliations

Yuechen Jiang1 · Enze Zhang2,3 · Mohsinul Kabir1 · Chenying Lin2,3 · Ying Peng2,3 · Fengyuan Liu2,3 · Qianqian Xie2,3 · Stavroula Golfomitsou4 · Konstantinos Arvanitis1 · Sophia Ananiadou1,5

1 University of Manchester2 School of Artificial Intelligence, Wuhan University3 Cognitive Language and Information Lab, Wuhan University4 Getty Conservation Institute5 ELLIS Manchester

Cite Pothen
@misc{jiang2026pothen,
  title={Pothen: Can Vision-Language Models Tell Where a Cultural Object Comes From?},
  author={Yuechen Jiang and Enze Zhang and Mohsinul Kabir and Chenying Lin and Ying Peng and Fengyuan Liu and Qianqian Xie and Stavroula Golfomitsou and Konstantinos Arvanitis and Sophia Ananiadou},
  year={2026},
  url={https://arxiv.org/abs/2604.07338}
}
← → to explore · Esc to close