I ended up using gnugo --score aftermath --capture-all-dead to determine
the final state of the board. Thanks to Petr for the suggestion! This
worked within a 1pt margin of error for probably 95% of the games, which
was good enough for my purposes.
-Justin
The Maddison et al, and Clark et. al. papers,
http://arxiv.org/pdf/1412.6564v2.pdf
http://arxiv.org/abs/1412.3409,
both suffer from a lack of very high skilled games, and thus result to
using (possibly blitz) games from lower ranked players on KGS. Has there
been any effort to gather data from the
