STS - Important problem with scoring of STS2

General discussion about computer chess...
Post Reply
User avatar
Robert Houdart
Posts: 180
Joined: Thu Jun 10, 2010 4:55 pm
Contact:

STS - Important problem with scoring of STS2

Post by Robert Houdart » Thu Jul 15, 2010 1:43 pm

There is a major problem with the scoring of STS2 by STSStat which is apparent when you look at the results.

For example:
Image

For STS2 the best move is found 88/100, but this gets a Score/1000 of only 861 (less than 10 times the "best move found" count). For all other STS the "Score/1000" is always higher than 10 times the best move hit.

The problem comes from typos in the STS2.epd file which make STSStat work incorrectly for at least 9 positions.
For positions 31, 41, 55, 62, 78 the "c0" comment contains a full move instead of a short move (e.g. "Bb7c8=10" instead of "Bc8=10").
For positions 32, 45, 93 the "c0" comment comes after the "id" text, and the comment starts with a space.
For position 28 the best move Bf8 only gets 8 points, whereas Rc2 gets 10 points.

Hope this helps,
Robert

User avatar
Swaminathan
Posts: 375
Joined: Wed Jun 09, 2010 12:14 pm

Re: STS - Important problem with scoring of STS2

Post by Swaminathan » Thu Jul 15, 2010 4:14 pm

Thanks, I'll forward this to Dann.

Hopefully we will come up with new update.
Logo made by Ulysses P (Vytron)
Co-Authored with Dann Corbit: Strategic Test Suite

User avatar
Swaminathan
Posts: 375
Joined: Wed Jun 09, 2010 12:14 pm

Re: STS - Important problem with scoring of STS2

Post by Swaminathan » Wed Jul 21, 2010 8:34 am

We have updated the STS2 file with some new positions and bug fixes.

http://sites.google.com/site/strategict ... s/STS2.epd
Logo made by Ulysses P (Vytron)
Co-Authored with Dann Corbit: Strategic Test Suite

User avatar
Robert Houdart
Posts: 180
Joined: Thu Jun 10, 2010 4:55 pm
Contact:

Re: STS - Important problem with scoring of STS2

Post by Robert Houdart » Wed Jul 21, 2010 11:17 am

Thank you, very useful!

Robert

Post Reply