Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Test suites - can they reliably predict ELO?

Author: Enrique Irazoqui

Date: 04:26:56 12/12/99

Go up one level in this thread


On December 12, 1999 at 06:57:55, blass uri wrote:

>On December 12, 1999 at 06:26:50, Enrique Irazoqui wrote:
>
>
><snipped>
>>My test has by now 130 positions not included in any other test and took me 11
>>months so far to put it together, and quite a bit longer to figure it out, so
>>you can imagine that I feel quite reluctant to throw it to the garbage. But it
>>is a bit of a catch 22 situation: If I don't publish it, no one will trust it;
>
>
>I do not think that noone will trust it.
>There is a simple way to check it.
>You can publish the rating of chess programs based on your test suite
>and we will see if the ssdf results of the same programs are going to be the
>same if people are going to see that the ssdf rating are almost the same then
>people are going to trust it.
>
>Uri

I already did this twice, the last time on November 17th, 9 days before the SSDF
published their latest list. The difference bewteen both were quite
insignificant and well within the margin of error.

Enrique



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.