Author: KarinsDad
Date: 13:25:17 01/26/99
Go up one level in this thread
On January 26, 1999 at 16:03:15, Bruce Moreland wrote: > >On January 26, 1999 at 15:54:03, KarinsDad wrote: > >>If Bionic and Crafty were 95% similar, but Bionic and Fritz were 93% similar, >>what have you proved? > >With three programs so far we are getting similarities of 60-63%. If this >holds, and yet Crafty returns with 85%, I think it would argue that Bionic is >not very dissimilar to Crafty, in an evaluation/search sense. I'm glad that you are running other programs against the control. At what times are you running the programs, on what type and speed processors, and what is your matching criteria? > >If everything came back around 60%, including Crafty, it would put the onus on >Bob to figure out why he got a 100% result when he did a related test some time >ago. And of course a detailed comparison of those 3 games that Robert used (the rest of the games are irrelevent with regard to what Robert found, you can only compare his tests with tests on the games he checked). > >It wouldn't indicate that the amount of work done on the program is sufficient >to negate Bob's authorship. Of course not. > >In any case, I'm interested in seeing what the result will be, aren't you? Yes, with details. > >Statistical insignificance is also an interesting conclusion. Yup. > >bruce KarinsDad
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.