@article{thescalinglawofevaluationfailurewhysimpl,
  title = {The Scaling Law of Evaluation Failure: Why Simple Averaging Collapses Under Data Sparsity and Item Difficulty Gaps, and How Item Response Theory Recovers Ground Truth Across Domains},
  author = {Jung Min Kang},
  year = {2026},
  eprint = {2605.11205},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11205},
}