Author: Roberto Nerici
Date: 00:34:41 12/01/03
Go up one level in this thread
On December 01, 2003 at 01:03:10, Steven Edwards wrote: >The recent fiasco [snip] A good non-opinionated way to start the post... >The clear need here is for a method that does not depend on subjective human >evaluation of similarity of play or upon the random accusation of a non-biased >party. My proposal is instead to use a test suite to provide a performance >fingerprint of all the entrants in a competition. Apologies in advance if I am missing something, but this doesn't seem to address the issue of a program which uses a significent part of another program, only whether a program is sufficiently similar in its evaluation and search to play similarly. If program B takes the book, interfacing and learning parts of program A, but has a completely different eval and search, then it can be considered a heavily plaguarised (sorry if I've spelled that wrong) effort, but the proposal would not detect that. I also don't think it would detect a problem with program B if its eval and search were based on program A but were heavily modified. However, to me, even if it did, I don't think it would have helped in the Craft/List "incident". Pleas feel free to correct me if I'm wrong... Roberto/.
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.