Programmers Open Letter to ICGA on Rybka/Fruit

[Uly]

You may be correct that the public release was later. This version seems simply to be the last beta from Fabien. It does date from Nov 2005, however. I don't know if the testing groups might have got this "beta" version earlier than public, or not.

I recall that the Fruit 05/11/03 Beta had different parameters, and was much weaker, and only at a much later point it was set to the strength close ro Rybka 1.0 Beta. We're talking 2007 or something (akin to a CM9000 personality being released 2 years later and saying that original CM9000 was much stronger at release date, here the "05/11/03" would just be misleading as no Fruit at that strength existed in 05/11/03).

Anyway, it could also be just my faulty memory, I hope an expert on Fruit story can comment.

[benstoker]

[...] Do you consider the Elo lead Rybka had (over commercial Fruit) at this date to be significant?

http://www.computerchess.org.uk/ccrl/40 ... t_all.html

Rybka 1.0 Beta 32-bit	2893	+14	−14	65.2%	−108.5	30.8%	2061
Fruit 05/11/03 	        2888	+12	−12	49.8%	+1.3	34.5%	2637

http://www.husvankempen.de/nunn/40_40%2 ... liste.html

340 	Fruit 05/11/03       	2819 	13 	13 	1724 	50.5% 	2815 	40.3%
351 	Rybka 1.0 Beta w32 	2815 	6 	6 	7357 	59.3% 	2750 	34.7%

http://iggor.110mb.com/ratings/NIL42_alph.txt

0    12 Fruit 05/11/03 HD1-2 UCI       : 2803   21  21   558    52.0 %   2789   47.7 %
0    21 Rybka 1.0 Beta UCI             : 2757   20  20   743    54.2 %   2728   35.4 %

To my surprise, when I brought up the Elo difference last year, no one picked up on it.

On a different subject: Serious concerns have been raised regarding Bob being a judge on the ICGA panel that will render final opinion on the matter. These are legitimate complaints given the fact that he has already publicly expressed his opinion, and therefore must recuse himself.

Franklin

That's why there are THREE panelists. Did you know that committees in Congress are comprised of not just Republicans, but also Democrats? Isn't that amazing. Did you know that extremely biased judges sit on appellate courts? Guess what - there's never just ONE appellate judge presiding over a case. At a minimum three, up to 9. Guess what. The US Supreme Court has 9 justices. Guess what. Most city councils have extremely biased councilmembers. Imagine that! Guess what. There's always more than one councilmember! Ain't that nifty! Guess what. Regulatory agency administrative hearings are usually presided over by no more than and not less than - count 'em up dawg - 3, that's THREE, administrative hearing officers. Ain't that just nifty. I wonder why society seems to always have more than one judge, or one judge whose decisions are subject to review by a panel of other judges. Hmmm. I wonder what that's all about! Could it be that society has come to expect people are biased. Is bias wrong? Or, does the adversarial process, the argument and counterargument between extremely biased, opposing views produce the closest we can hope to get to accepted truth in judgment? Indeed, this process will be all the MORE reliable BECAUSE Hyatt is on the panel. We KNOW that at least ONE panelist will not be a mere shill, stooge, comrade, apparatchik for monied interests. That is a very satisfying fact. And, we KNOW that the monied interests, fanboys, and just plain ol' reasonable folk will speak up and challenge the evidence presented, and judgments or opinions offered, and, yes, any bias perceived. There is bias everywhere! No escape from bias.

So, shut up about bias.

[BB+]

On a different subject: Serious concerns have been raised regarding Bob being a judge on the ICGA panel that will render final opinion on the matter. These are legitimate complaints given the fact that he has already publicly expressed his opinion, and therefore must recuse himself.

That funky word "must" again... Originally I was ambivalent about this, but now that it has transpired that there is evidence that pre-Fruit Rybkas contained significant portions of Crafty, there could be a heightened danger of Bob "wearing two hats" (both as an "investigator" and a "moderator").

[BB+]

I recall that the Fruit 05/11/03 Beta had different parameters, and was much weaker, and only at a much later point it was set to the strength close ro Rybka 1.0 Beta. We're talking 2007 or something (akin to a CM9000 personality being released 2 years later and saying that original CM9000 was much stronger at release date, here the "05/11/03" would just be misleading as no Fruit at that strength existed in 05/11/03).

Anyway, it could also be just my faulty memory, I hope an expert on Fruit story can comment.

I agree that it would be nice to get the Fruit timeline correct. Is there a date on Fruit 2.2 or Fruit 2.3? I get "Aug 1st 2007" on the executable of "05/11/03" from the Fruit page, but that need not mean anything. The Fruit history page is not completely clear here, but it seems to suggest Nov 2005:

It made its first appearance to the public in March 2004. Fruit was then just a basic program with a very simple evaluation and basic search. However since then it made skirmish progress adding about 100 Elo to each new release (1.5, 2.0, 2.1 and Fruit 2.2). The latest version from Fabien is "Fruit Beta 05/11/07" compiled on November, the 3rd 2005. Since then no new versions where released.

Fruit 2.2 has dates in late Sep 2005 on the files (I think this is when it went commercial), and with Fruit 2.2.1 it is late Oct 2005. I get the latter as 2854 in CCRL 40/4 and 2843 in CCRL 40/40.

[thorstenczub]

That's why there are THREE panelists. Did you know that committees in Congress are comprised of not just Republicans, but also Democrats? Isn't that amazing.

consider they take away the rybka championship titles.
and the 2nd programs get the title.

hiarcs will get a title. and harvey williamson is in the panel.
he is a member of the hiarcs team.

so this gives an interest conflict.

would the american system allow that the mother of a murderer is in the jury ?

[clumma]

I agree that it would be nice to get the Fruit timeline correct.

Fruit 2.x was in Sept. 2005. Rybka 1.0 beta, Dec. of that year. Commercial version of Fruit was available before commercial version of Rybka (I bought both as soon as they were available). Rybka 1.0 beta was modestly stronger than first commercial Fruit release -- on the order of 20-50 Elo. I don't recall a 64-bit Rybka 1.0 beta but that may be because I didn't have x64 Windows until 2008.

It's funny you mention Stockfish - I think it is essentially a Fruit-type engine (not Glaurung, but Stockfish). Ditto Fritz versions 9 and later. Speculation on my part of course. Hiarcs and Shredder strike me as truer to their original form.

-Carl

[Hood]

but why is HW in the panel, is he a chess programmer ?

[Jeremy Bernstein]

but why is HW in the panel, is he a chess programmer ?

Not the Panel. He's on the Secretariat, which I guess is some sort of Council of Elders which arbitrates/manages any investigations: they don't perform any investigative function themselves, but (attempt to) gather any evidence, using the Panel as an investigative tool and present the collected findings to the IGCA board(?). I disagree with the choice of Harvey for such a task, given his rabid partisanism on these matters in the past, but that's apparently a done deal. Bob isn't exactly the least outspoken member of the CC community, either.

[Hood]

It looks that HW is not the best choice . He has problems with accepting opinions of others.

I think not only Rybka shall be checked . May be programms of some people who signed the letter, either.

I suppose that a derivation is not to avoid in current world.

It looks that the policy of Rybka forum has turned against it.

[Jeremy Bernstein]

It looks that HW is not the best choice . He has problems with accepting opinions of others.

I think not only Rybka shall be checked . May be programms of some people who signed the letter, either.

I suppose that a derivation is not to avoid in current world.

It looks that the policy of Rybka forum has turned against it.

Indeed. My only reason for suggesting that an analysis of HIARCS or Shredder would be a good idea is to create some sort of "control" situation (I don't believe that HIARCS or Shredder are guilty of any code copying, from Fruit or anywhere else). Mostly so that "the public" could understand why this number and type of identical features is conspicuous, unusual and a reasonable basis for calling a piece of software a "clone" or "derivative".

jb