BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices. Reuel, A., Hardy, A. F., Smith, C., Lamparth, M., Hardy, M., & Kochenderfer, M. J. CoRR, 2024.
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices. [link]Link  BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices. [link]Paper  bibtex   1 download  
@article{journals/corr/abs-2411-12990,
  added-at = {2025-01-01T00:00:00.000+0100},
  author = {Reuel, Anka and Hardy, Amelia F. and Smith, Chandler and Lamparth, Max and Hardy, Malcolm and Kochenderfer, Mykel J.},
  biburl = {https://www.bibsonomy.org/bibtex/2f7faf5b634c0749eeecefb01c958aa33/dblp},
  ee = {https://doi.org/10.48550/arXiv.2411.12990},
  interhash = {cb39a5dd7cf268f00e364f9df54a2cf4},
  intrahash = {f7faf5b634c0749eeecefb01c958aa33},
  journal = {CoRR},
  keywords = {dblp},
  timestamp = {2025-01-06T07:06:05.000+0100},
  title = {BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices.},
  url = {http://dblp.uni-trier.de/db/journals/corr/corr2411.html#abs-2411-12990},
  volume = {abs/2411.12990},
  year = 2024
}

Downloads: 1