Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Errors in Test Suites (Re: WAC test suite statistics for Mchess 7)

Author: Robert Hyatt

Date: 10:19:20 01/15/98

Go up one level in this thread


On January 15, 1998 at 08:06:18, Ernst A. Heinz wrote:

>On January 15, 1998 at 07:54:12, Robert Hyatt wrote:
>
>> [...]  At least 10 it missed I don't
>>agree with, because of huge tactical scores for what is supposedly the
>>wrong move...
>
>Yes, there are a couple of these in ECM, WCSAC, and others.
>
>I always take them as they are because I often suspect that the
>solution moves are really deep mates.
>
>We should probably try to generate "reference" versions of all these
>suites -- just as Amir suggested in an earlier post.
>
>Any volunteers out there to coordinate such efforts?
>
>=Ernst=

I'm going to do a "ECM-derivative" test suite.  I'm going to try to
cull the 1 second positions first, and whatever else it takes to get
this into the < 500 position range, although I'd really prefer a 300
position suite like WAC, so that it doesn't take forever to run.

I'll be happy to post what I come up with, and also to take suggestions
on what to exclude to make it managable...



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.