@InProceedings{gp-benchmarks-2012,
  author = 		 {James McDermott and David R. White and Sean Luke and
                  Luca Manzoni and Mauro Castelli and Leonardo
                  Vanneschi and Wojciech Ja\'skowski and Krzysztof
                  Krawiec and Robin Harper and Kenneth De Jong and
                  Una-May O'Reilly},
  title = 		 {Genetic Programming needs better benchmarks},
  booktitle={Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference},
  pages={791--798},
  year = 	 {2012},
  address = 	 {Philadelphia},
  publisher = {ACM}
}

@Article{gp-benchmarks-2013,
  author = 		 {David R.~White and James McDermott and Mauro
                  Castelli and Luca Manzoni and Brian W.~Goldman and
                  Gabriel Kronberger and Wojciech Ja{\'s}kowski and
                  Una-May O'Reilly and Sean Luke},
  title = 		 {Better GP Benchmarks: Community Survey Results and Proposals},
  journal = 	 {Genetic Programming and Evolvable Machines},
  year = 		 {2013},
  Volume= {14},
  Issue={1},
  pages={3--29},
  doi = {10.1007/s10710-012-9177-2},
  abstract = {We present the results of a community survey regarding
                  genetic programming (GP) benchmark
                  practices. Analysis shows broad consensus that
                  improvement is needed in problem selection and
                  experimental rigor. While views expressed in the
                  survey dissuade us from proposing a large-scale
                  benchmark suite, we find community support for
                  creating a ``blacklist'' of problems which are in
                  common use but have important flaws, and whose use
                  should therefore be discouraged. We propose a set of
                  possible replacement problems.}
}