HPC-ED: Testing Automated Agents to Assess the Quality of Training Resource Metadata

Volume 17, Issue 1 (March 2026), pp. 34–41

Download PDF

@article{jocse-17-1-5,
  author={Habiba Morsy and Essence Toone and Charlie Dey and Zilu Wang and Mary Thomas and David Joiner},
  title={HPC-ED: Testing Automated Agents to Assess the Quality of Training Resource Metadata},
  journal={The Journal of Computational Science Education},
  year=2026,
  month=mar,
  volume=17,
  issue=1,
  pages={34--41},
  doi={https://doi.org/10.22369/issn.2153-4136/17/1/5}
}

We present a proof-of-concept system for automating quality assurance in the HPC-ED federated training catalog using large language models (LLMs). The HPC-ED catalog system integrates metadata crawling, video transcript extraction, and model-based evaluation to score and provide recommendations on metadata quality at scale.