I test on IGS, and I also see a lot of cheating against the computer. Many Faces does its own scoring and transmits dead stone status. This prevents people from not indicating their dead stones. Many Faces keeps track of people who escape without finishing a game and won't accept matches from them. Almost all match requests will be from weaker players, which will force the rating down, so after each match, Many Faces makes one match request to a person one rank stronger.
Even with this there is a bias down in the ratings. I can start a new version of Many Faces 3 or more ranks higher and it will win more than half its games. Many Faces is currently 13k* on Igs (as ManyFaces). David > -----Original Message----- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of > Erik van der Werf > Sent: Wednesday, December 06, 2006 2:36 AM > To: computer-go > Subject: Re: [computer-go] language choices > > > On 12/6/06, Magnus Persson <[EMAIL PROTECTED]> wrote: > > Note that to get these data I deleted all games where > Valkyria lost on > > points, because close to 100% of those games were not scored > > correctly. I do not know if it is incompetence or outright > cheating, > > but it happens a lot. Fortunately Valkyria always resigns when it > > loses so it easy to filter out those game. > > I found that humans tend to cheat a lot against computers in > the scoring phase. This used to be the case on NNGS (my > thesis contains some statistics on that if you're > interested), and I don't see any reason why this should now > be different on KGS, unless of course if computer players now > have the same rights in the scoring phase as humans... > > Erik > _______________________________________________ > computer-go mailing list > computer-go@computer-go.org > http://www.computer-go.org/mailman/listinfo/computer-go/ > _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
