Code accompanying the paper Quantitative Evaluation of Motif Sets in Time Series by Daan Van Wesenbeeck, Aras Yurtman, Wannes Meert and Hendrik Blockeel (KULeuven). This repository (currently) includes code for the proposed evaluation method PROM, the existing evaluation metrics score and correctness, and our benchmark dataset generation procedure which can be used to reconstruct the proposed benchmark (see notebook generating_the_benchmark.ipynb).