In this work, we propose a first approach and benchmarks to tackle this challenge.

Public benchmarks play an essential role in the evaluation of large language models.

Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this hierarchy, treating labels as permutation invariant.

In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks.