A Stevens's Power Law Check-up of GPT-5.5's Implicit Reading of Visual Encoding
We adapt Stevens's power law to measure the implicit ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of algorithmic models.
Key points
- In our pilot study, AIs see no legend.
- In the color conditions, no colormap name is provided either.
- GPT-5.5 first views a reference visual representation and estimates its magnitude, then estimates the magnitude of each subsequent image of the same representation relative to that reference.
- Our evaluation of twelve visual variables makes how algorithmic models read visual encodings measurable, comparable with human perception, and more transparent to humans.
Sources (1)
- [1]A Stevens's Power Law Check-up of GPT-5.5's Implicit Reading of Visual EncodingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 01:52 PM
We adapt Stevens's power law to measure the implicit ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of algorithmic models.
In our pilot study, AIs see no legend.
Extractive summary: sentences quoted from the sources.