@article{whycomparingsingleperformancescoresdoes,
  title = {Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches},
  author = {Nils Reimers and Iryna Gurevych},
  year = {2018},
  eprint = {1803.09578},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1803.09578v1},
}