Is Belka a Rybka?

[GenoM]

Maybe Belka include parts of fruit that strelka does not have.

As far as I'm aware Belka is exact copy of Strelka with modifications without added code of fruit.

[Harvey Williamson]

This is good enough for me. I will no longer be testing Strelka now that Vas has publicly made this statement.

Regards, Graham.

Hi Graham,

I think you have made the right decision. Will CCRL discuss stopping testing this? As if even 1 member does the results are still presented as being by the CCRL group. If individuals play with strelka that is one thing. If even 1 person in a major testing group tests this and the results are added to the CCRL rating list then to a casual observer it appears that the whole group supports the engine.

It is hard enough for commercial authors to make a living these days. And those that work full time like Mark, Stefan, Amir and Vas do not need to see someone taking advantage of their hard work. This kind of engine appearing in a major rating list can only help to drive the main authors out of business.

Best Wishes,

Harvey

[Graham Banks]

This is good enough for me. I will no longer be testing Strelka now that Vas has publicly made this statement.

Regards, Graham.

Hi Graham,

I think you have made the right decision. Will CCRL discuss stopping testing this? As if even 1 member does the results are still presented as being by the CCRL group. If individuals play with strelka that is one thing. If even 1 person in a major testing group tests this and the results are added to the CCRL rating list then to a casual observer it appears that the whole group supports the engine.

It is hard enough for commercial authors to make a living these days. And those that work full time like Mark, Stefan, Amir and Vas do not need to see someone taking advantage of their hard work. This kind of engine appearing in a major rating list can only help to drive the main authors out of business.

Best Wishes,

Harvey

My post in the Rybka forum:

Hi Vas,

I've made an individual decision not to test Strelka further based on your post here plus other information I won't disclose, but that I know you're aware of. However, I'd like you to publicly state that you've examined the source code of Strelka to complete the picture for me.

Also my decision is only an individual one. All CCRL testers must make their own decision as Ray has stated.

CCRL is not just about rating lists. It's also about providing all sorts of statistical data. Although the ponder hit stats between Rybka and Strelka show a close correlation, there are similar questions that could be asked of other engines also.
Because of the legal implications that could arise, it is obviously in the group's interest to stay clear of making statements or assumptions based on such data.

Ray is quite correct with what he says.

Regards, Graham.

[ozziejoe]

I agree Harvey. Every strelka-like engine takes away from the hard work of the true engine authors. And it hurts interest in computer chess.


My understanding is that uri had decomplied strelka and is attempting to use some ideas in it to improve movei. I think this is fine, as uri has a long history as an original author and, from what i understand, it is not illegal to decompile. Also, he would use strelka/rybka beta to inform how he designs his program (rather than merely recreating a program)

J

[Andrej Sidorov]

My understanding is that uri had decomplied strelka

No, he got sources from author.

[ozziejoe]

he got the sources from the author? is it legal to decompile another person's software and then give that decompile to someone else?

I do not understand much about these cloning laws.

J

[GenoM]

Every strelka-like engine takes away from the hard work of the true engine authors. And it hurts interest in computer chess.

Its simply not true. It's irritating to me when people with little knowledge about this case make brave generalisations about computer chess. Joseph, you even did not knew that Uri has the sources of Strelka send him with the author's permission. So before making statements like this its better to make some research about the case.
Regards,
Geno

[Tony]

Here is an interesting experiment. Talke Belka 1.8.13. It comes with two files. One is a header file (EvalConsts.h) describing what some variables do. Although the comments ar ein Russian, I had a Bulgarian friend translate the comments for me. Variable names are very close to what is used in the Piece Square Table (PST.cpp) file that comes with Fruit. For example:

extern int BishopLine[8];

in Fruit this is:

static const int BishopLine[8] = {
-3, -1, +0, +1, +1, +0, -1, -3,
};

In fact, most of the names appear in Fruit and have the same apparent meanings. There are som new terms (not a lot), sveral involving a more detailed passed pawn evaluation.

So, I go to thinking. the person.txt file lets you set new values to be used for any of the terms in person.txt. If you have an empty person.txt, it reverst all values to whatever the defaults are. You can quikly figure out what the default values are by putting numbers in one line like this:

BishopLine 0 0 0 0 0 0 0 0

that would set these values to all 0. You then run a short search to a fixed depth, change the values and run again. When I did this, and used the fact written here that 3399 is a "pawn", so 33.9 would be 1/100 th a pawn (used in Fruit), the values for BishopLine when divided by 33.9 come out to:

-3, -1, 0, 1, 1, 0,-1, -3

Exactly the values used in Fruit 2.1. And this is true for all the "Line" variables I tried, and many of the other constants as well. If Belka is a clone it certainly has a lot of Fruit in it.

This seems to be evidence that the author starte dwith Fruit as a model, which I think was mentioned here.

Note that I looked at the code of strelka1.8 and did not find the string
BishopLine inside of it

I also looked for [8] because it may have a different name and I found no names that are about piece square table and I found only names that are about passed pawns.

Maybe Belka include parts of fruit that strelka does not have.

Uri

Duh,

if Belka is Strelka, and Belka has variables that your sourcecode of Strelka does not have THEN YOU HAVE NOT BEEN GIVEN THE CORRECT SOURCECODE.

It must have been an accident, since the author is very trustworthy and there is no reason why he would have different code checked for cloning.

Tony

[Andrej Sidorov]

if Belka is Strelka, and Belka has variables that your sourcecode of Strelka does not have THEN YOU HAVE NOT BEEN GIVEN THE CORRECT SOURCECODE.

It must have been an accident, since the author is very trustworthy and there is no reason why he would have different code checked for cloning.

Tony

What а silly statement. Uri Blass compiled sourcecode and get exact Strelka executable. Do you think he's idiot?

[matejst]

7 Loop 13.6 32-bit – Fruit 2.2.1 75.8 1186
8 Loop 10.32f – Fruit 2.2.1 75.6 1018
9 Toga II 1.2.1a – Glaurung 2 epsilon/5 64-bit 75.6 336
10 Delphil 1.6c – Arion 1.7 74.7 352
11 Loop M1-T 64-bit 4CPU – Toga II 1.3.1 73.4 1306
12 Loop M1-T 64-bit 2CPU – Toga II 1.3.1 72.7 1532
13 Rybka 1.0 64-bit – Strelka 1.8 71.4 1875
14 Toga II 1.3.1 – Loop 13.6 32-bit 70.8 960
15 Loop 13.6 32-bit – Fruit 2.3.1 70.3 519
16 Fritz 9 – Zap!Chess Reykjavik 32-bit 70.2 346
17 Loop 13.6 64-bit 4CPU – Toga II 1.2.1a 70.0 1914
18 Loop M1-T 64-bit 4CPU – Toga II 1.2.1a 69.7 1582


This part of a table about the ponder hit correlation from ccrl doesn't have to mean much, of course, but shouldn't we take it in account when we are thinking about clones?

I am absolutely convinced that if Osipov name was Gunther or John, if he had not tried to show the way V. R. made his engine (and demonstrated that V. R. heavily used Fruit open code) but, instead, had eliminate some bugs in Strelka, changed just one evaluation parametar and made it commercial, nobody would have talked about clonning.

I have to add that nobody one this forum knows precisely what clonning is. Let's make a decision, via a pool, maybe: is it the use of the code (complete or partial), a similar output, or something else. And then, stick to this decision.

bs