FIDE Rules on ICGA - Rybka controversy

[Chris Whittington]

I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

How is "beyond any reasonable doubt" the right standard? Who gets to decide?

I'll take that bet slightly reworded. YOU prove that he did NOT design the code as I speculated. ... Because now the onus would be on YOU. And it is an absolute certainty that you can't prove someone didn't so something. And NO, his word would NOT be proof.

I was actually going to comment on this issue (as Mr. Schröder had desired), but I see it has been derailed. Anyway, I still have not heard from a GM (evidently more useful than a mere IM, otherwise I might even have asked Levy ) regarding the chessic notion.

But I haven't seem a program that gives NO PENALTY AT ALL for any double pawn in the middle game and only in the endgame.

There is NO midgame code in Rybka.

Midgame in Rybka is an interpolation of opening (24 phase units) and endgame (0 phase units). Rybka gives a (nonzero) penalty for a doubled pawn once any piece has been captured (on a pure phase basis, 24/25th of time, or 96% which would round up ). Furthermore, EVAL_COMP is primarily about features, not about numerical tuning. In this sense, Fruit and Rybka (and Faile and ExChess) use the "same" doubled pawn feature, while some other engines listed are of a more varying nature.

Considering the absence of an unique Fruit eval feature

All the engines involved have a "unique" backward/weak pawns feature. It is something for which there is a lot of scope for variations in implementation. Fruit/Rybka was higher than the "typical" amount of overlap.

the similarity with Rybka is exactly 0.0

If you wish to calibrate the scoring in that way, you are free to do so. You then end up with only (nearly) exact matches at 1.0, and Fruit/Rybka has (significantly) more of these than any other pair. I personally think adding in partial scores is a superior method. [For that matter, recall that most of the Panel did not particularly find EVAL_COMP's quantification of the situation to be necessary, and it was largely produced in response to comments by van Kervinck and Roberson].

I would say your 0.8 for the rook-pawn code is an outrageous mistake. And I'm being kind calling it a mistake. You do realise the chessic difference between the codings, and that you shoehorned the Rybka code into a category it should not be in, just to be able to "parallelise" (falsely) the two programs?

As to the rest of your COMP EVAL, its hard to know where even to begin in criticising it. Not even wrong comes to mind. But, again rook-pawn is an example - why no FILTERING? You do understand copyright law, and by extension the non-existent plagiarism law haha, allows for many cases where similar/identical does not mean copied and should be scrapped from consideration? Why no filter-scrapping?

[Rebel]

I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

How is "beyond any reasonable doubt" the right standard? Who gets to decide? .

Vas!

He wrote it.

Or so it is ASSUMED...

On his behalf I collect 15% provision.

[hyatt]

That was not a chess lesson. It was "RE nonsense". If you read what he wrote, he SPECIFICALLY discussed the difference between a bit board implementation and a mailbox implementation. Something we said we EXPLICITLY abstracted away. A loop vs an AND mask? Bit board vs mailbox, nothing more, nothing less.

So please don't call that a "lesson" to someone who actually teaches programming. That was more of a "chess obfuscation" than anything else. Zach did it exactly right there. I don't think much of the "seems to be, or appears to be" nonsense. It is or it isn't.

Your question two posts back in that thread is also nonsensically phrased. You snipped just the 4 bit-wise ANDs (tst instructions) and left out the rest. You DID realize that the masks and stuff were loaded at the top of the code? You seem almost surprised that some rather convoluted mailbox code collapses into 4 AND operations in a bit board program. This is quite common. I've used the term "bit-parallel" because bit boards let me ask a question with one AND that would take a loop with multiple if-statements inside in a mailbox program. That's part of the attractiveness of bit boards for those of us that decided to invest the time to get comfortable with them.

And you are missing it again, you only look at the code and not what the code does. If you had read Marcel carefully you would had seen Fruit and Rybka are evaluating different, Fruit has the exception code for second ranked pawns that can advance 2 squares. Rybka has not, just a quick and dirty evaluation. Fabien uses the Kmoch definition, Vas not. Does the name Hans Kmoch and his basic stuff about pawns every chess player needs to know mean anything anythng to you? There is even a whole page on the CPW about him.

You see, there is this pattern, you ASM geeks (of which I belong too) only look at the code and shout EUREKA!, this piece of Rybka code smells to similarity with Fruit and then you forget to look what the code actually evaluates, as in this case.

So my statement still stands:

COMP EVAL fails to mention that EVERY eval ingrediënt in Fruit and Rybka is coded DIFFERENTLY even after substraction of the Mailboard / Bitboard differences.

Next one?

You miss MY point. Do you know why Rybka doesn't do that? Not so convenient in bitmaps. A pretty natural part of conversion from one to the other. I had several such things that were in Cray Blitz but which I left out of Crafty because (a) it was not clear if they were really beneficial and (b) it was more complicated (affecting speed) to do it the same way. Taking both of those into consideration...

BTW we didn't say "smells to similarity." We said "they do the same thing" or in a few cases "almost exactly the same thing but there is one difference."

The rook scoring (open/half-open files) is a good example. I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

If you want to hang on to that "every" simply because the code doesn't match, and it obviously could NOT match when using two different board representations" then that's up to you. I know better.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

I can hear the cluck-cluck noises already.

I thought about this overnight. I'll take that bet slightly reworded. YOU prove that he did NOT design the code as I speculated. I can hear the cluck-cluck noises already. Because now the onus would be on YOU. And it is an absolute certainty that you can't prove someone didn't so something. And NO, his word would NOT be proof.

Ah, the bet!! You want to do it, or just trying to pretend not to be big chicken? hahaha?

So, Hyatt makes some convoluted negation to the logic, where I am either quite lost in parsing, or too lazy to work out. In plain English what exactly are you proposing the bet to be? Is it balance of probabilities I have to exceed, or are you going to be so lacking in confidence you need beyond reasonable doubt, and what exactly is the proposal? It appears to be, "I need to prove that he did not copy the code and make an outright translation error" - right? On balance of probabilities? 51% It's irregular, because this assumes him guilty unless he can prove innocent, but that is Hyatt VIG bias all along, I suppose ....

Is that your bet? $25,000 or $50,000?





*

You want to make a lame bet that requires ME to prove something that can't be proven, and if I fail, you win. I proposed a REVERSAL. You get to try to prove something that can not possibly be proven either, and then YOU lose. I have no idea where that 51% nonsense came from, NOT from me however.

You can NOT prove that someone did NOT do something. You can't prove with 100% confidence that someone DID something. This is the type of bet that would lead to a never-ending argument, something _I_ am not willing to waste time on.

You just want to act infantile.

When does the "I triple-dog dare you" come into play??? (of course, according to the TV that would be a minor breach of etiquette as you should FIRST "double-dog dare me.")

[hyatt]

Code: Select all

         FRUIT                                 RYBKA
         if (doubled) {                        if (doubled) endgame -= 158
            opening[me] -= DoubledOpening;
            endgame[me] -= DoubledEndgame;

There is NO midgame code in Rybka. In your document it is rewarded as a 100% similarity with Fruit.

How do you KNOW there is no "middle game code in Rybka"? If that value is tuned to zero, the compiler would optimize it out.

I am tired of assumptions. It's not there. Period.

But I understand how your VIG mind works.

He is always guilty no matter what.

You just ASSUME and the VIG world according to Bob is okay again.

Right?

"If the facts don't fit the theory, change the facts."
--Albert Einstein

It's what you are doing here.

What _I_ am doing? Do you remember the discussion with Richard Vida where it became painfully obvious you knew little about modern optimizing compilers? You state unequivocally that "it is not there". With nothing to support that.

Simple piece of code:

#include <stdint.h>
int mg_score, eg_score;
uint64_t pattern, board;
dummy() {
if (pattern & board) {
mg_score += 0;
eg_score += 20;
}
}

Here is what gcc -O produces:

testq %rdx, (%rax)
je L3
movq _eg_score@GOTPCREL(%rip), %rax
addl $20, (%rax)

If you replace the 0 and 20 constants by variable names that are declared as constants, exactly the same result.

"it is not there". In the compiled output. but it _is_ there in the original. How can you assume which is correct (it is not or it it there)?? And ALL you can do is assume without original source. So if WE assume it might have been there, we are doing something wrong. But when YOU assume it is NOT there, that's perfectly OK? That sounds quite distorted to me. And notice that if this is left out, the +20 is STILL a part of the score, since the final result is interpolated between 0 and 20 depending on how much material is left. Looking carefully, I would not call it 100%. but I WOULD call it 75%. Certainly not 0% which is a total distortion of what is there.

As far as Einstein's quote, YOU need to think about that a bit, because YOU are changing the facts as much as I am. 75% is FAR closer to the truth than 0%. 0% is pure nonsense.

[Chris Whittington]

That was not a chess lesson. It was "RE nonsense". If you read what he wrote, he SPECIFICALLY discussed the difference between a bit board implementation and a mailbox implementation. Something we said we EXPLICITLY abstracted away. A loop vs an AND mask? Bit board vs mailbox, nothing more, nothing less.

So please don't call that a "lesson" to someone who actually teaches programming. That was more of a "chess obfuscation" than anything else. Zach did it exactly right there. I don't think much of the "seems to be, or appears to be" nonsense. It is or it isn't.

Your question two posts back in that thread is also nonsensically phrased. You snipped just the 4 bit-wise ANDs (tst instructions) and left out the rest. You DID realize that the masks and stuff were loaded at the top of the code? You seem almost surprised that some rather convoluted mailbox code collapses into 4 AND operations in a bit board program. This is quite common. I've used the term "bit-parallel" because bit boards let me ask a question with one AND that would take a loop with multiple if-statements inside in a mailbox program. That's part of the attractiveness of bit boards for those of us that decided to invest the time to get comfortable with them.

And you are missing it again, you only look at the code and not what the code does. If you had read Marcel carefully you would had seen Fruit and Rybka are evaluating different, Fruit has the exception code for second ranked pawns that can advance 2 squares. Rybka has not, just a quick and dirty evaluation. Fabien uses the Kmoch definition, Vas not. Does the name Hans Kmoch and his basic stuff about pawns every chess player needs to know mean anything anythng to you? There is even a whole page on the CPW about him.

You see, there is this pattern, you ASM geeks (of which I belong too) only look at the code and shout EUREKA!, this piece of Rybka code smells to similarity with Fruit and then you forget to look what the code actually evaluates, as in this case.

So my statement still stands:

COMP EVAL fails to mention that EVERY eval ingrediënt in Fruit and Rybka is coded DIFFERENTLY even after substraction of the Mailboard / Bitboard differences.

Next one?

You miss MY point. Do you know why Rybka doesn't do that? Not so convenient in bitmaps. A pretty natural part of conversion from one to the other. I had several such things that were in Cray Blitz but which I left out of Crafty because (a) it was not clear if they were really beneficial and (b) it was more complicated (affecting speed) to do it the same way. Taking both of those into consideration...

BTW we didn't say "smells to similarity." We said "they do the same thing" or in a few cases "almost exactly the same thing but there is one difference."

The rook scoring (open/half-open files) is a good example. I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

If you want to hang on to that "every" simply because the code doesn't match, and it obviously could NOT match when using two different board representations" then that's up to you. I know better.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

I can hear the cluck-cluck noises already.

I thought about this overnight. I'll take that bet slightly reworded. YOU prove that he did NOT design the code as I speculated. I can hear the cluck-cluck noises already. Because now the onus would be on YOU. And it is an absolute certainty that you can't prove someone didn't so something. And NO, his word would NOT be proof.

Ah, the bet!! You want to do it, or just trying to pretend not to be big chicken? hahaha?

So, Hyatt makes some convoluted negation to the logic, where I am either quite lost in parsing, or too lazy to work out. In plain English what exactly are you proposing the bet to be? Is it balance of probabilities I have to exceed, or are you going to be so lacking in confidence you need beyond reasonable doubt, and what exactly is the proposal? It appears to be, "I need to prove that he did not copy the code and make an outright translation error" - right? On balance of probabilities? 51% It's irregular, because this assumes him guilty unless he can prove innocent, but that is Hyatt VIG bias all along, I suppose ....

Is that your bet? $25,000 or $50,000?





*

You want to make a lame bet that requires ME to prove something that can't be proven, and if I fail, you win. I proposed a REVERSAL. You get to try to prove something that can not possibly be proven either, and then YOU lose. I have no idea where that 51% nonsense came from, NOT from me however.

You can NOT prove that someone did NOT do something. You can't prove with 100% confidence that someone DID something. This is the type of bet that would lead to a never-ending argument, something _I_ am not willing to waste time on.

You just want to act infantile.

When does the "I triple-dog dare you" come into play??? (of course, according to the TV that would be a minor breach of etiquette as you should FIRST "double-dog dare me.")

You were the one proposing a "bet". I called your bluff. You want to change the terms of the bet. Bluff called again. Chicken out each time.

Right, so your position that Rybka rook-pawn code is a "bug created by mistranslation" is all just so much bullshit. Actually the code is smart, IM-smart and you and your gang of non chess programmers didn't see it. None of you were chess players, chess differences, huge chess differences just passed you by. Watkins,Zach and Hyatt.

[Rebel]

lol Bob, I was actually WAITING you to come up with the compiler excuse.

It's an ASSUMPTION man, deal with it.

Give it up.

For once

[Chris Whittington]

I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

How is "beyond any reasonable doubt" the right standard? Who gets to decide?

I'll take that bet slightly reworded. YOU prove that he did NOT design the code as I speculated. ... Because now the onus would be on YOU. And it is an absolute certainty that you can't prove someone didn't so something. And NO, his word would NOT be proof.

I was actually going to comment on this issue (as Mr. Schröder had desired), but I see it has been derailed. Anyway, I still have not heard from a GM (evidently more useful than a mere IM, otherwise I might even have asked Levy ) regarding the chessic notion.

But I haven't seem a program that gives NO PENALTY AT ALL for any double pawn in the middle game and only in the endgame.

There is NO midgame code in Rybka.

Midgame in Rybka is an interpolation of opening (24 phase units) and endgame (0 phase units). Rybka gives a (nonzero) penalty for a doubled pawn once any piece has been captured (on a pure phase basis, 24/25th of time, or 96% which would round up ). Furthermore, EVAL_COMP is primarily about features, not about numerical tuning. In this sense, Fruit and Rybka (and Faile and ExChess) use the "same" doubled pawn feature, while some other engines listed are of a more varying nature.

Considering the absence of an unique Fruit eval feature

All the engines involved have a "unique" backward/weak pawns feature. It is something for which there is a lot of scope for variations in implementation. Fruit/Rybka was higher than the "typical" amount of overlap.

the similarity with Rybka is exactly 0.0

If you wish to calibrate the scoring in that way, you are free to do so. You then end up with only (nearly) exact matches at 1.0, and Fruit/Rybka has (significantly) more of these than any other pair. I personally think adding in partial scores is a superior method. [For that matter, recall that most of the Panel did not particularly find EVAL_COMP's quantification of the situation to be necessary, and it was largely produced in response to comments by van Kervinck and Roberson].

COMP EVAL was written as part of a mission? Isn't that otherwise known as bias? In particular when the biased researcher has the opportunity to select the comparator programs, the evaluation component categories (since when is abort king attack test on less than Q plus minor piece a category btw?) amd the little subjective comparator numbers. Your ability to frig the test results is clear. On what basis are we expected to accept your choices?

[Rebel]

I would say your 0.8 for the rook-pawn code is an outrageous mistake. And I'm being kind calling it a mistake.

Yup.

Let's consider the main message Zach and Mark uttered :

Mark Watkins: I think the case for "copyright infringement" (or plagiarism) of the evaluation function as a whole is quite weighty, particularly when combined with the various other Fruit 2.1 bits that appear here-and-there in Rybka 1.0 Beta.

Zach Wegner: Simply put, Rybka's evaluation is virtually identical to Fruit's.

Then there are 2 ways to write an EVAL_COMP, the way Mark did, measuring the similarity between 8 engines, OR a SINGLE measuring between the 2 itself BASED on the accusation above. You get total different numbers.

Ain't that so?

[hyatt]

That was not a chess lesson. It was "RE nonsense". If you read what he wrote, he SPECIFICALLY discussed the difference between a bit board implementation and a mailbox implementation. Something we said we EXPLICITLY abstracted away. A loop vs an AND mask? Bit board vs mailbox, nothing more, nothing less.

So please don't call that a "lesson" to someone who actually teaches programming. That was more of a "chess obfuscation" than anything else. Zach did it exactly right there. I don't think much of the "seems to be, or appears to be" nonsense. It is or it isn't.

Your question two posts back in that thread is also nonsensically phrased. You snipped just the 4 bit-wise ANDs (tst instructions) and left out the rest. You DID realize that the masks and stuff were loaded at the top of the code? You seem almost surprised that some rather convoluted mailbox code collapses into 4 AND operations in a bit board program. This is quite common. I've used the term "bit-parallel" because bit boards let me ask a question with one AND that would take a loop with multiple if-statements inside in a mailbox program. That's part of the attractiveness of bit boards for those of us that decided to invest the time to get comfortable with them.

And you are missing it again, you only look at the code and not what the code does. If you had read Marcel carefully you would had seen Fruit and Rybka are evaluating different, Fruit has the exception code for second ranked pawns that can advance 2 squares. Rybka has not, just a quick and dirty evaluation. Fabien uses the Kmoch definition, Vas not. Does the name Hans Kmoch and his basic stuff about pawns every chess player needs to know mean anything anythng to you? There is even a whole page on the CPW about him.

You see, there is this pattern, you ASM geeks (of which I belong too) only look at the code and shout EUREKA!, this piece of Rybka code smells to similarity with Fruit and then you forget to look what the code actually evaluates, as in this case.

So my statement still stands:

COMP EVAL fails to mention that EVERY eval ingrediënt in Fruit and Rybka is coded DIFFERENTLY even after substraction of the Mailboard / Bitboard differences.

Next one?

You miss MY point. Do you know why Rybka doesn't do that? Not so convenient in bitmaps. A pretty natural part of conversion from one to the other. I had several such things that were in Cray Blitz but which I left out of Crafty because (a) it was not clear if they were really beneficial and (b) it was more complicated (affecting speed) to do it the same way. Taking both of those into consideration...

BTW we didn't say "smells to similarity." We said "they do the same thing" or in a few cases "almost exactly the same thing but there is one difference."

The rook scoring (open/half-open files) is a good example. I'd bet that was an outright error in translation, seeing as how it is actually a -25 Elo change.

If you want to hang on to that "every" simply because the code doesn't match, and it obviously could NOT match when using two different board representations" then that's up to you. I know better.

Bet taken. $25,000 that you can't prove beyond any reasonable doubt that the Rybka rook-pawn code we were discussing was a "outright error in translation" within the next two months. I'll send you my lawyers address, we can both deposit $25,000 each. The $50,000 goes to me when you lose, else vice versa.

I can hear the cluck-cluck noises already.

I thought about this overnight. I'll take that bet slightly reworded. YOU prove that he did NOT design the code as I speculated. I can hear the cluck-cluck noises already. Because now the onus would be on YOU. And it is an absolute certainty that you can't prove someone didn't so something. And NO, his word would NOT be proof.

Ah, the bet!! You want to do it, or just trying to pretend not to be big chicken? hahaha?

So, Hyatt makes some convoluted negation to the logic, where I am either quite lost in parsing, or too lazy to work out. In plain English what exactly are you proposing the bet to be? Is it balance of probabilities I have to exceed, or are you going to be so lacking in confidence you need beyond reasonable doubt, and what exactly is the proposal? It appears to be, "I need to prove that he did not copy the code and make an outright translation error" - right? On balance of probabilities? 51% It's irregular, because this assumes him guilty unless he can prove innocent, but that is Hyatt VIG bias all along, I suppose ....

Is that your bet? $25,000 or $50,000?





*

You want to make a lame bet that requires ME to prove something that can't be proven, and if I fail, you win. I proposed a REVERSAL. You get to try to prove something that can not possibly be proven either, and then YOU lose. I have no idea where that 51% nonsense came from, NOT from me however.

You can NOT prove that someone did NOT do something. You can't prove with 100% confidence that someone DID something. This is the type of bet that would lead to a never-ending argument, something _I_ am not willing to waste time on.

You just want to act infantile.

When does the "I triple-dog dare you" come into play??? (of course, according to the TV that would be a minor breach of etiquette as you should FIRST "double-dog dare me.")

You were the one proposing a "bet". I called your bluff. You want to change the terms of the bet. Bluff called again. Chicken out each time.

Right, so your position that Rybka rook-pawn code is a "bug created by mistranslation" is all just so much bullshit. Actually the code is smart, IM-smart and you and your gang of non chess programmers didn't see it. None of you were chess players, chess differences, huge chess differences just passed you by. Watkins,Zach and Hyatt.

Fine. I triple-dog dare you to go away and not come back. As far as what I believe concerning Rybka, the possible mis-translation is just an idea. A mistake _I_ made more than once in creating Crafty from a mailbox program. Whether it is right or not only ONE person on the planet knows. And from all his claims of originality that have been shown to be completely false, who would believe him if he did state what happened here?

[hyatt]

I would say your 0.8 for the rook-pawn code is an outrageous mistake. And I'm being kind calling it a mistake.

Yup.

Let's consider the main message Zach and Mark uttered :

Mark Watkins: I think the case for "copyright infringement" (or plagiarism) of the evaluation function as a whole is quite weighty, particularly when combined with the various other Fruit 2.1 bits that appear here-and-there in Rybka 1.0 Beta.

Zach Wegner: Simply put, Rybka's evaluation is virtually identical to Fruit's.

Then there are 2 ways to write an EVAL_COMP, the way Mark did, measuring the similarity between 8 engines, OR a SINGLE measuring between the 2 itself BASED on the accusation above. You get total different numbers.

Ain't that so?

No. Because then the question would be "how similar are others?" He tried to answer that. The PANEL folks that raised the issue made that suggestion. Otherwise you would be complaining "But we don't know how others fare when compared like this." And I do not see how you would get "totally different results". You get "more results" since there are more programs in the mix.