Die Schwalbe

37 problem(s) found in 2299 milliseconds (displaying 37 problem(s)). [COMMENTDATE>=20220810 AND G='Retro' AND NOT K='Cross-capture' AND A='Buchanan, Andrew'] [download as LaTeX]

1 - P1001038
Andrew Buchanan
4v Retros mailing list 21/01/2001
P1001038
(14+1) C+
Last move?
#2
1. 0-0 Kxe2 2. Te1#
R: 1. Ke4-e3
play all play one stop play next play all
Die vorherige Stellung war noch nicht tot, wenn Weiß noch rochieren darf.
AB: First proof of "can castle", without recourse to conventions. (2009-11-22)
A.Buchanan: deadpos doesn't understand about retro logic yet, so does not eliminate R: 1. Ke4xLSBe3? (2022-11-13)
more ...
comment
Keywords: Dead Position, Castling, Rex solus (s), Obvious promotion (L), Last Move?, Type B
Genre: Retro, 2#
Computer test: HC+ Forward Popeye 4.79 DP deadpos
FEN: 8/7Q/8/4BB2/2PP1P2/3NkN2/PP2P1P1/4K2R
Reprints: 13 idee & form 156, p. 5284, 10/2022
Input: Gerd Wilts, 2001-01-25
Last update: A.Buchanan, 2023-12-27 more...
2 - P1294321
Andrew Buchanan
www.anselan.com 2001
P1294321
(1+2)
Black to move. Last move?
R: 1. Kb8xSa8
play all play one stop play next play all
Compare P0001033.
Gerald Ettl: steht der sLh5 vielleicht auf h2 ?? (2023-07-02)
SCHRECKE: Why not R: Kb8xLa8? (2023-07-03)
Mario Richter: Wie "SCHRECKE" mit seiner Frage schon illustriert hat: mit dem sL auf h2 wäre das Problem inkorrekt, da neben R: 1. Kb8xSa8 auch R: 1. Kb8xLa8 als letzter Zug möglich gewesen wäre. Grund sind die etwas verwirrenden Dead-Reckoning-Regeln: mit sLh5 kann zuletzt nicht Kb8xLa8 geschehen sein, da in der Stellung wKb8 - sKb6 sLh5 sLa8 wegen der unzureichendes-Material-zum-Mattsetzen-Regel das Spiel schon in dieser Position beendet gewesen wäre, der wK als gar nicht mehr zur Ausführung eines Zuges geommen wäre ... (2023-07-03)
Mario Richter: Dear James, I suggest that you undo last change and put the black bishop back on h5! (2023-07-03)
A.Buchanan: There are 17 valid squares for the wB. Got to be on a light square for reasons given. Also it can't occupy or attack c8. And can't be attacking a8 because BTM. I think h5 selection was random, but could argue for any. (2023-07-04)
A.Buchanan: Or maybe bBa4, with which White by his last move avoided a completely sound #12. (2023-07-04)
Gerald Ettl: Dann waere es vielleicht ganz sinnvoll man schreibt die Bedingung unter das Diagramm. (2023-07-04)
A.Buchanan: Hi Gerald, it's not a condition, it's a FIDE rule since 1997, invented by a problemist who is also a rules committee member (Igor Vereschchagin) and approved by the rules committee (headed by FIDE Head International Arbiter Stewart Reuben), backed up by a WFCC convention since 2015 (Kjell Widlert & Michel Caillaud, responding to a request from some endgame studiers who understood that it was a real thing. Like 50M rule, it applies by default for retro problems. And the PDB keywords here give the game away anyway. If it was a forward stipulation, then I would indeed add a stipulation, e.g. P1208623. Please enjoy the madness that is DP rule :) P.S. I have found recently that it was really invented by Shakespeare. (2023-07-04)
Gerald Ettl: Ich spiele nicht nach den FIDE-Regel. (2023-07-04)
Olaf Jenkner: Allright.
https://www.skat-online.com/regeln-hilfe/regelwerk/internationale-skatordnung.html (2023-07-05)
comment
Keywords: Type B, Last Move? (KxS), Dead Position, Economy record (Last Move? Type B), Rex solus (W), Aristocrat, Miniature, Minimal
Genre: Retro
FEN: K7/8/1k6/7b/8/8/8/8
Reprints: Retros mailing list 20/02/2007
Input: A.Buchanan, 2015-01-07
Last update: James Malcom, 2023-07-03 more...
3 - P1324999
Andrew Buchanan
9v Problemas 12, p. 285, 10/2015
after Hauke Reddmann
P1324999
(2+2)
Illegal position.
White to move.
How does the game end?

Author's "Solution" from Problemas magazine [edited]:
"White has no move, and is not in check. But for stalemate to apply, and end the game, it basically requires that the move producing the position was legal (see Law A5.2a). Not only is the position illegal, but no legal last move exists, even from a previously illegal position! So we are stuck in some kind of limbo. The result can perhaps be described as “nearly stalemate”.
Hauke Reddmann described a position like this as “dividing by zero”. It's an exception to the general observation that one can continue to play chess if the wrong player is in check. It seems odd to insist that only the final move in a game has to be legal, but that’s what the rules do. And I think that’s as far down the rabbit hole as we should go today."
Not Thema Null, because set play does not already achieve the stipulation.
A.Buchanan: The forward rules can apply perfectly well to illegal positions (e.g. set play, where we never concern ourselves with the position's legality). But a lacuna comes where a position with no precursor position is delivering mate, stalemate or DP. A #0 should work as well as a #2. In all cases, the FIDE Laws currently require that the prior move (and only that move) be legal. The Law is about catching errors/cheating otb, so I think the Codex should ensure it does not get carried over to problem chess. This problem will then lose its point, but it will have served its purpose and it can be retired to Golden Age, much to Henrik's relief :) (2023-12-15)
comment
Keywords: Lese Majeste, Illegal position, Dead Position, Miniature
Genre: Retro
FEN: 8/8/8/8/8/nk6/P7/K7
Input: A.Buchanan, 2016-09-06
Last update: A.Buchanan, 2019-12-09 more...
4 - P1348600
Andrew Buchanan
chess.stackexchange.com 23/3/2018
P1348600
(12+12) C+
PG in 20.0
1. d4 c5 2. f4 e5 3. f5 d5 4. Lf4 Le6 5. fxe6 exf4 6. e4 f5 7. e5 c4 8. Ld3 Lc5 9. dxc5 cxd3 10. c4 a5 11. b4 a4 12. Db3 axb3 13. a4 b5 14. a5 h5 15. g4 Th6 16. g5 d4 17. gxh6 g5 18. h4 g4 19. Ta4 Dg5 20. hxg5 bxa4 example
play all play one stop play next play all
A shortest game to reach 16 passed pawns
Henrik Juel: Euclide 1.01 confirms that no shorter proof game exists
It seems that the moves are unique, so a challenging part b) suggests itself: How many solutions? (2018-03-27)
A.Buchanan: Thanks, Henrik. Your b) would be challenging indeed! Usually if I make a problem "how many solutions?", the purpose of the problem is to showcase some combinatorial identity, and the play would be structurally simpler.
A different direction is to ask: how many *diagrams* exist that could illustrate the same point: 16 passed pawns in 20.0 moves? I think the answer, including this one, is 12.
Another much harder question is whether one can push the surviving officers around to make a longer but unique proof game. (2018-03-28)
Henrik Juel: 16 passed pawns come in (at least) two varieties
1. A pawn position where all pawns could promote without further captures
2. A pawn position where PxP captures (except possibly ep) are no longer possible
Andrew's definition is probably the latter (2018-03-28)
A.Buchanan: Sorry I don't understand this distinction. (2018-03-28)
Henrik Juel: They are not mutually exclusive, 2 implies 1
Type 1 would apply to your PG, also if the white pawns on the c and e files were lowered to c2,c3 and e2,e3
In type 1 'passed' is interpreted as 'allowing 16 free promotions'; it is equivalent to a game with 8 pawn captures, 1 from each file
To reach type 2, some pawn may have to advance further (2018-03-28)
A.Buchanan: OIC: in the context of playing the game, definition 2 is what counts, because no PxP captures are possible. The only question in people'e minds in stackexchange is whether doubled pawns can count as being passed. The assessment is that they can. (2018-03-28)
Moldenhauer: Computerprüfung: Cooked Diagrammstellung Stelvio 1.31.
Keine Lösung: BP 19.5.
Beispiel: 1. b4 a5 2. d4 a4 3. e4 b5 4. Bd3 c5 5. f4 c4 6. f5 cxd3 7. Bf4 d5
8. c4 e5 9.Qb3 Be6 10. fxe6 Bc5 11. dxc5 axb3 12. a4 d4 13. a5 exf4
14. Ra4 bxa4 15. g4 h5 16. g5 Rh6 17. gxh6 g5 18. e5 g4 19. h4 Qg5 20. hxg5 f5 (2023-06-18)
A.Buchanan: Thanks Moldenhauer. This is "obviously" a non-unique proof game, but there's no syntax in stipulations to distinguish between them. There is also sometimes the notion that a non-unique PG must force some thematic content, but that's not the case here, as the content is visible in the target diagram. So I interpret your Stelvio as C+ for this humble problem. Thanks again. (2023-06-21)
comment
Keywords: Construction record, Non-Unique Proof Game
Genre: Retro
Computer test: Computerprüfung: Non-unique solution Diagrammstellung Stelvio 1.31. Keine Lösung: BP 19.5
FEN: rn2k1n1/8/4P2P/P1P1PpPp/pPPp1pp1/1p1p4/8/1N2K1NR
Input: A.Buchanan, 2018-03-27
Last update: A.Buchanan, 2023-06-21 more...
5 - P1398779
Andrew Buchanan
AA006 The Hopper Magazine I01 24/12/2021
P1398779
(12+5) cooked
h=3*

play all play one stop play next play all
Cook: Set: 1. ... Th1 2. Ka1 Dg1/Tg1 3. Ka2 Df1=/Th1=
Main: 1. Ka1 Th1 2. Ka2 Dg1/Tg1 3. Ka1 Df1=/Th1=
A.Buchanan: Oops! Vlaicu Crisan informed me of a bug in the forward play. Not so easy to fix, but think I've managed. Sent back to Vlaicu, and will republish in The Hopper. (2022-12-03)
comment
Keywords: Draw by repetition, Superseded by (P1408741)
Genre: Retro, Fairies
FEN: 8/p7/8/8/8/P4P1P/kPPPPRPr/2KnrQR1
Input: A.Buchanan, 2022-01-31
Last update: Miguel Ambrona, 2023-07-26 more...
6 - P1398780
Andrew Buchanan
AA007 The Hopper Magazine I01 24/12/2021
P1398780
(16+15)
Drawn game. PG in 9.0
Moldenhauer: Computerprüfung: C- oder Cooked Stelvio 1.4 in 1 Sekunde.
Die Diagrammstellung ist verschieden erreichbar.
Hier 2 Möglickeiten:
1.Sa3 d5 2.Sb1 Kd7 3.f3 De8 4.Kf2 e5 5.Kg3 De6 6.Kh4 Dg6
7.Kh3 e4 8.fxe4 f6 9.e5 Ke8+
1.Sa3 d5 2.Sb1 Dd6 3.f3 Da6 4.Kf2 Sd7 5.Kg3 Dg6+ 6.Kh4 e5
7.Kh3 e4 8.fxe4 f6 9.e5 Sb8+ (2023-07-29)
A.Buchanan: Hi Moldenhauer this problem is sound. You are forgetting the constraint: "Drawn game". (2023-07-29)
Moldenhauer: Hi Andrew, ich habe deshalb nur die Diagrammstellung angegeben.
Ich hoffe Andrew ist erlaubt! Mein Vorname ist Klaus. (2023-07-29)
A.Buchanan: Hi Klaus nice to meet you, thanks for all your work. The point of HC+ is that it combines human & computer logic intelligently. It makes zero sense to solve robotically for 9.0. It is definitely valuable to solve this kind of stipulation (1) as PG in 5.0, and then (2) as PG A-B for 2.0. Apparent duals can then be resolved through reasoning about castling, e.p. and premature draw. (2023-07-29)
comment
Keywords: Draw by repetition, Unique Proof Game, Constrained problem, Castling, En passant (not!)
Genre: Retro
FEN: rnb1kbnr/ppp3pp/5pq1/3pP3/8/7K/PPPPP1PP/RNBQ1BNR
Input: A.Buchanan, 2022-01-31
Last update: Miguel Ambrona, 2023-07-26 more...
7 - P1398939
Edgar Fielder
Andrew Buchanan

Discord Chess Problems & Studies Server 07/022022
EF, version AB
P1398939
(13+10)
h#1
R: 1. Dg4-g3 Kd8-e8 2. Dg5-g4 Kc8-d8 3. Dg6-g5 Kb7-c8 4. Df6-g6 Tb8-h8 5. De6-f6 Kc8-b7 6. Dd6-e6 Kd8-c8 7. Dc6-d6 Ke8-d8 8. Db6-c6 Kf8-e8 9. Da7-b6 Kg8-f8 10. Db7-a7 Te8-b8 11. Db8-b7 Tf8-e8 12. b7-b8=D 0-0 13. c6xDb7 Da8-b7 14. d5xLc6 Dd8-a8 15. d4-d5 Lb7-c6 16. e3xSd4 Lc8-b7 17. f2xSe3 c6-c5 18. h5-h6 b7xLc6 is one of many possible histories, but all involve hidden castling
play all play one stop play next play all
Retro solution (which works for Fielder's original too).
Pawn captures: white missing LSBf, captured by axbxc,bxc. Therefore wBf captured at least 3 times fxexdxc, also exd & sLf8 died at home. So one missing black unit unaccounted for currently.
Cage can only be unlocked by exd3, but wLf must be returned home prior to this. Can only be uncaptured by sBb7xLc6-c5. If wPf did not promote, it was captured by sBa on b6 after 5 captures or on c5 after 4 captures. The latter is not possible, as wBc4 never left its file. The former is not possible, because sD would be unavailable for capture until b7xc6, which only happened after the cage was formed.
Therefore wBf promoted, and must have captured four times to reach b-file, accounting for the final capture. When it promoted on b8, sBb had already moved, capturing wLf and therefore the cage was already formed. So wDg3 is the promoted unit. If wBexd3 was capture of sLc, then there is deadlock between the two releases of bishops, so sLc was captured by wBf, hence path to promotion shifted to light squares (i.e. via c6 not b6) so sBc5 was already in place. When b7-b8=D, all the other White pieces (except possibly for wPh6, bK & bRh8) were already in place.
There is now a time-critical retraction, as White has at most 7 moves (not 9, because must release wRh before wLf is free) before sBb7xLc6, with sD & sLc sealed inside. So R: 1. b7-b8=D ~ 2. c6xDb7 zB Da8-b7 3. d5xLc6 Dd8-a8 4. d4-d5 Lb7-c6 5. e3xSd4 Lc8-b7 6. f2xSe3 c6-c5 7. h5-h6 b7xLc6. Where was bK while all this was happening. There is only one spare tempo (h4-h5) If bK was off the back rank, there was not enough time to retract back there. So the only possibility is that Black was already castled, and can uncastle when the black cage is closed. The missing move can be R: 1. ... 0-0.
Since castling is illegal in the forward play, h#1 is unique with Donati theme as wQ revisits the promotion square:
1. c6 Db8# not
1. 0-0? Dxg7#
cheeky retro-active version of P0001136
A.Buchanan: Looking at the original, I am wondering why wBh cannot be on h5. It clearly cannot retract to h3, but how many times is it needed to retract if White retracts from the critical position 1Q3rk1/2pppppp/8/2p4P/2P5/PPRP4/RBpP1PP1/N1K5 (2022-02-07)
A.Buchanan: Maybe the distinguished composer felt that the more spare White moves has, the more creditable is the fact that Black had no way to avoid prior castling. The problem is still sound either way. Of course, with the h#1 version, wBh6 is mandatory. wD location was pretty much arbitrary in the original, but now there is only one wD location for soundness: g3. (e5 & g4 are unsound). (2022-02-07)
A.Buchanan: The solution given in Keym’s wonderful “Eigenartige Schachprobleme” uses an unnecessary move by wPh. (2022-02-23)
A.Buchanan: In offering this version, I do not think that pure retros are in anyway inferior to forward problems, which was perhaps the motivation for forward stipulations in the days of yore. Rather, the aesthetic tension between past and future never tires for me. It is not an issue to me whether the balance of interest in a retro-active problem be equally divided between the two directions. Rather, it’s essential that the position have two readings: that the pieces have two purposes. This formal requirement of double meaning which is ubiquitous and quotidian in a cryptic crossword should also find a place near to the hearth in chess problems. So Morse might welcome Dexter. (2022-02-23)
more ...
comment
Keywords: Cant Castler, Castling Paradox (hidden sK), Donati Theme (wD), Castling in the retro play (wk)
Genre: h#, Retro
Computer test: Substantial retro thinking to show castling illegal + trivial v4.87 for forward play
FEN: 4k2r/2pppppp/7P/2p5/2P5/PPRP2Q1/RBpP2P1/N1K5
Input: A.Buchanan, 2022-02-07
Last update: A.Buchanan, 2023-08-15 more...
8 - P1401711
Andrew Buchanan
OP008 The Hopper Magazine I01 24/12/2021
"Ak ja, retten, retten; hvad hjælper det, at du har retten, når du ikke har nogen magt?"
P1401711
(3+3) C+
h#2.5 (2 solutions)
Position after Black's 5,696th move
1. ... Se6 2. Th2 Ta8 3. Th7 Txe8#
1. ... Txa2 2. Lg6 Tg2 3. Lh7 Sf7#
not 1. ... 0-0-0 2. Lg6 Tg1 3. Lh7 Sf7#?? (game just ended by 50M)
play all play one stop play next play all
A full solution is really too big for PDB, but it is available at https://www.thehoppermagazine.com/AA084
Henrik Juel: solutions
1...Sg5-e6 2.Ra2-h2 Ra1-a8 3.Rh2-h7 Ra8*e8 #
1...Ra1*a2 2.Be8-g6 Ra2-g2 3.Bg6-h7 Sg5-f7 #
not 1...0-0-0? 2.Be8-g6 Rd1-g1 3.Bg6-h7 Sg5-f7 #
because White has lost his right to castle, as Andrew will explain, I hope... (2023-07-29)
A.Buchanan: White has not necessarily lost the right to castle, but if he can castle then the 50M rule triggers before the mate can be executed. It is pretty complicated, sorry. (2023-07-29)
A.Buchanan: We don't do mottoes much these days. Mrs Baird was a big fan. On page 301 of the July 1916 Chess Amateur P.H. Williams wrote:
"I think it was Mrs Baird who did more to search Shakespeare for accidental (or deliberate) reference to chess, since all her retractors had Shakespearean mottoes, and her knowledge of the Avonian bard was obviously extensive. Her example was followed by other composers of retractors, who considered such positions would be incomplete without some reference to the poet."
But there are other great playwrights, and Asteroid 5696 was named after one such, whose bitter quotation accurately states this problem's theme. (2023-07-31)
Henrik Juel: The citation is by danish philosopher Søren Kierkegaard (1813-1855) and means something like
Oh yes, to be right, to be right; it does not help much that you are right, when you have no power. (2023-07-31)
Henrik Juel: Asteroid 5696 is named Ibsen after the norwegian playwright Henrik Ibsen (1828-1906), who must have borrowed the citation from Søren Kierkegaard (2023-07-31)
A.Buchanan: Thanks for this Henrik - I resolved the question here: https://philosophy.stackexchange.com/questions/101229/did-ibsen-originate-this-statement
Beyond the castling try, the other innovation here is in the solution beginning 1...Se6. Castling convention and 50M I think are trying to combine by Retro Strategy (being optimistic about 50M rights like we are with castling, rather than pessimistic like we are with ep). (2023-08-04)
more ...
comment
Keywords: Aristocrat, Miniature, 50 move rule, Castling, Exchange of roles (T/S, Guard/Mate), Chumakov theme (l/t, simplified), Retro Strategy (RS), Model mate (2), Constrained problem
Genre: h#, Retro
Computer test: HC+ Popeye 4.61 and analysis
FEN: 4b2k/8/8/6N1/8/8/r7/R3K3
Reprints: AA084 The Hopper Magazine I04 13/07/2023
Input: A.Buchanan, 2022-06-09
Last update: A.Buchanan, 2023-08-27 more...
9 - P1405296
Andrew Buchanan
Andrey Frolkin

AA042 The Hopper Magazine I02 23/06/2022
P1405296
(13+9)
First move of wRb2?
R: 1. g2xBh3 h4-h3 2. Te2-b2 h5-h4 3. 0-0-0-0-0-0 h6-h5 4. e7-e8=T h7-h6 5. f6xDe7,f6xL/Se7
play all play one stop play next play all
https://drive.google.com/file/d/1e6e77hAXxKajrJdu5Rd3hdsA0k3QSH9D/view
Thanks to Mario Richter for finding a bug, now fixed by switching pawns g-h files
more ...
comment
Keywords: Type A, First Move?, Staugaard castling, Economy record
Genre: Retro, Fairies
FEN: n2N4/PPkp1pp1/PNBp4/Bp1p4/1p6/4K2P/PR5P/7R
Input: James Malcom, 2022-10-20
Last update: A.Buchanan, 2023-07-27 more...
10 - P1407176
Andrew Buchanan
Retros mailing list 01/01/2023
P1407176
(16+0)
ser-PG in 19
How many solutions?
1. a4 2. Ta3 3. d4 4. h4 5. Thh3 6. Thf3 7. Tf6 8. f4 9. f5 10. Lf4 11. e3 12. Lc4 13. Ld5 14. c4 15. Db3 16. Db6 17. b4 18. Tb3 19. b5 for example
play all play one stop play next play all
2023 solutions
Joost de Heer: See Problemas april 2023 for a detailed explanation on how to calculate the number of solutions. (2023-04-04)
A.Buchanan: Hi Joost thanks for the comment. This problem basically is about "triangle + triangle = square", but the article uses a different mechanism (Elastic Belt) to reach the same number (2023-04-05)
comment
Keywords: Path enumeration (year), Seriesmover, Non-Unique Proof Game
Genre: Retro, Mathematics
FEN: 8/8/1Q3R2/1P1B1P2/P1PP1B1P/1R2P3/6P1/1N2K1N1
Input: A.Buchanan, 2023-01-08
Last update: A.Buchanan, 2023-08-27 more...
11 - P1407446
Andrew Buchanan
Discord Chess Problems & Studies Server 25/01/2023
to Siegfried Hornecker
P1407446
(9+9)
A=>A in exactly 2.0 moves
16 solutions
Joost de Heer: In the diagram position, all castling rights are present. Each solution leads to a position with different castling rights remaining.

There are 4 different repetitions for white:
* 1. Rb1 2. Ra1 (Only white kingside castling still allowed)
* 1. Rh2 2. Rh1 (Only white queenside castling still allowed)
* 1. Kd2 2. Ke1 (No white castling allowed)
* 1. Sb6 2. Sc8 (All white castling allowed)

Similarly for black: 1. Rb8 2. Ra8 / 1. Rh7 2. Rh8 / 1. Kd7 2. Ke8 / 1. Sb3 2. Sc1

Each combination of these four results in a position with different castling rights, so 4*4=16 solutions.
There's one solution that breaks this pattern: all white castling allowed, no black castling allowed. Following the above scheme would result in the solution 1. Sb6 Kd7 2. Sc8 Ke8, but the first black move is not allowed, so this solution is slightly different: 1. Sd6 Kd7 2. Sc8 Ke8 (2023-02-07)
comment
Keywords: A to B, Symmetrical position, Asymmetrical solution
Genre: Retro
FEN: r1N1k1Nr/p3Pp2/7p/8/8/7P/P3pP2/R1n1K1nR
Input: A.Buchanan, 2023-01-27
Last update: A.Buchanan, 2023-01-27 more...
12 - P1407481
ChatGPT
Andrew Buchanan

Discord Chess Problems & Studies Server 29/01/2023
P1407481
(2+2)
#2
1. bxa3+ Kd4 2. Kb2#
play all play one stop play next play all
Chess problem by AI program ChatGPT

Q: Can you give an example of a chess retrograde analysis problem?

A: A retrograde analysis problem in chess is a problem where the goal is to determine the sequence of moves that led to a given position. For example:

White to move and mate in 2
[FEN "8/8/1p6/1P6/3k4/8/8/K7 w - - 0 1"]

In this problem, the goal is to determine the two moves (one for white and one for black) that led to the position shown. The solution is 1. bxa3+ Kd4 2. Kb2#
Henrik Juel: I do not understand this at all
It seems that ChatGPT is worthless for retro problems (2023-01-29)
A.Buchanan: Generally ChatGPT is amazing. We have entered a new age. Interacting with it reminds me of the first time I sent emails, or used a browser: we have crossed a frontier into engage with a function that will soon be commonplace. I already use it as a work tool for the last week. However it has limited skills and I was surprised it even attempted to construct a chess problem. It’s failure is humorous and kind of dreamlike (2023-01-30)
Henrik Juel: Thanks for your clarification, Andrew
ChatGPT is so amazing that it will give you a grade of B on some university exams; using it is obviously cheating, but do you enforce it?
In my youth calculators were developing fast; initially I banned the use of calculators in my OR exam, but the students were unhappy about it, saying that they were allowed in high school; I was forced to allow calculators, but then the poor students pointed out that the rich students had an unfair advantage; I then bought a few hundred cheap calculators and let the students borrow one for the exam (the rich students were still mad, but had to accept their lot in the social-democratic society of Danmark) (2023-01-30)
comment
Keywords: Joke, Kindergarten Problem, Minimal, Miniature
Genre: 2#, Retro
FEN: 8/8/1p6/1P6/3k4/8/8/K7
Reprints: Facebook 05/07/2023
Input: A.Buchanan, 2023-01-29
Last update: A.Buchanan, 2023-07-05 more...
13 - P1407693
Andrew Buchanan
R575 The Problemist 07/2021
P1407693
(14+12) C+
BP in 9.5
1. b4 e5 2. b5 La3 3. Lb2 d6 4. Lxe5 Lg4 5. Lxd6 Lxe2 6. Lf8 Lxb5 7. Ld3 Lc1 8. Lxh7 f5 9. Lxf5 Lf1 10. Lc8
play all play one stop play next play all
more ...
comment
Keywords: Unique Proof Game, Interchange (Ll Ll), bi-coloured Bristol, Line opening, Home-and-Away-Base, Belfort (LLll)
Genre: Retro
Computer test: C+ Stelvio 1.0
FEN: rnBqkBnr/ppp3p1/8/8/8/8/P1PP1PPP/RNbQKbNR
Input: Gunter Jordan, 2023-02-08
Last update: A.Buchanan, 2023-03-14 more...
14 - P1407694
Andrew Buchanan
R576 The Problemist 07/2021
P1407694
(12+13) C+
BP in 10.0
1. Sf3 Sc6 2. Se5 Sd4 3. Sxd7 Sxe2 4. Sb8 Sg1 5. Ld3 Dxd3 6. c3 Dxc3 7. Sxc3 Sf6 8. Sd5 Se4 9. Sxe7 Sxd2 10. Sg8 Sb1
play all play one stop play next play all
Henrik Juel: C++ Stelvio 1.0 (2023-02-08)
comment
Keywords: Unique Proof Game, Line opening, Interchange (Ss Ss), Home-and-Away-Base, Belfort (SSss)
Genre: Retro
FEN: rNb1kbNr/ppp2ppp/8/8/8/8/PP3PPP/RnBQK1nR
Input: Gunter Jordan, 2023-02-08
Last update: A.Buchanan, 2023-03-14 more...
15 - P1408358
Andrew Buchanan
10 Problemas 36, p. 1190, 10/2021
P1408358
(15+13) C+
PG in 14.5
1. e4 c5 2. Lb5 c4 3. Sf3 c3 4. 0-0 cxd2 5. c4 f6 6. Db3 d1=L 7. Lh6 Kf7 8. c5+ d5 9. cxd6ep+ Kg6 10. Se5+ Kh5 11. Le8+ g6 12. Lg7 Lh3 13. gxh3 Lg4 14. f3 Kh4 15. fxg4
play all play one stop play next play all
Objective: co-record shortest achievement of task, followed by artistic continuation.
Also version rnbqBbnr/pp2p1Bp/3P1pp1/4N2k/4P3/1Q5P/PP3P1P/RN1R2K1 PG in 14.0 mentioned in article. This offers different artistic continuation (with Pronkin instead of Ceriani-Frolkin).
more ...
comment
Keywords: Unique Proof Game, Valladao Task, Castling (wk), En passant, Promotion (l), Prenix (l), Ceriani-Frolkin Theme (l)
Genre: Retro
Computer test: HJ: C+ Stelvio 1.0
FEN: rn1qBbnr/pp2p1Bp/3P1pp1/4N3/4P1Pk/1Q5P/PP5P/RN3RK1
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-03-20 more...
16 - P1408359
Andrew Buchanan
9 Problemas 36, p. 1190, 10/2021
P1408359
(14+13) C+
PG in 12.0
1. e4 b5 2. e5 b4 3. Lb5 b3 4. Se2 bxc2 5. 0-0 cxb1=S 6. Dc2 f5 7. Dxc7 Kf7 8. Dc4 d5 9. exd6ep+ Kf6 10. Dxg8 Le6 11. d7 Dc8 12. d8=S Sd7
play all play one stop play next play all
Objective: co-record shortest achievement of task, followed by artistic continuation.
more ...
comment
Keywords: Unique Proof Game, Valladao Task, Castling (wk), En passant, Promotion (sS), Prenix (s), Phoenix (S)
Genre: Retro
Computer test: HJ: C+ Stelvio 1.0
FEN: r1qN1bQr/p2np1pp/4bk2/1B3p2/8/8/PP1PNPPP/RnB2RK1
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-03-20 more...
17 - P1408360
Andrew Buchanan
8 Problemas 36, p. 1190, 10/2021
P1408360
(13+13) C+
PG in 11.5
1. d3 e5 2. Sd2 e4 3. Sdf3 exf3 4. b4 fxe2 5. La3 exf1=S 6. Dg4 Ke7 7. 0-0-0 Kd6 8. b5+ c5 9. bxc6ep+ Kc7 10. Dxd7 Kb6 11. g4 Sg3 12. hxg3
play all play one stop play next play all
Objective: co-record shortest achievement of task, followed by artistic continuation.
more ...
comment
Keywords: Unique Proof Game, Valladao Task, Castling (wg), En passant, Promotion (s), Ceriani-Frolkin Theme (s)
Genre: Retro
Computer test: HJ: C+ Stelvio 1.0
FEN: rnbq1bnr/pp1Q1ppp/1kP5/8/6P1/B2P2P1/P1P2P2/2KR2NR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-03-20 more...
18 - P1408361
Andrew Buchanan
2 Problemas 36, p. 1189, 10/2021
P1408361
(15+13) C+
PG in 8.0
1. e4 Sf6 2. Ke2 Sd5 3. exd5 g5 4. d6 Lh6 5. dxc7 0-0 6. cxb8 Da5 7. Ke3 g4+ 8. f4 gxf3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to either minor officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sk), En passant
Genre: Retro
Computer test: HJ: with wSd8 C+ Stelvio 1.0
FEN: rn1P1rk1/ppp2p1p/3p1n1b/8/8/4Kp2/PPPP2PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
19 - P1408362
Andrew Buchanan
2 Problemas 36, p. 1189, 10/2021
P1408362
(15+13) C+
PG in 8.0
1. e4 Sf6 2. Ke2 Sd5 3. exd5 g5 4. d6 Lh6 5. dxc7 0-0 6. cxb8 Da5 7. Ke3 g4+ 8. f4 gxf3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to any officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sk), En passant
Genre: Retro
Computer test: HJ: with wSb8 C+ Stelvio 1.0
FEN: rPb2rk1/pp1ppp1p/7b/q7/8/4Kp2/PPPP2PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
20 - P1408363
Andrew Buchanan
3 Problemas 36, p. 1189, 10/2021
P1408363
(15+13) C+
PG in 8.0
1. d4 Sf6 2. Kd2 Se4+ 3. Ke3 Sc5 4. dxc5 g5 5. c6 Lh6 6. cxb7 0-0 7. bxc8 g4+ 8. f4 gxf3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to any officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sk), En passant
Genre: Retro
Computer test: HJ: with wSc8 C+ Stelvio 1.0
FEN: rnPq1rk1/p1pppp1p/7b/8/8/4Kp2/PPP1P1PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
21 - P1408364
Andrew Buchanan
4 Problemas 36, p. 1189, 10/2021
P1408364
(15+12) C+
PG in 8.0
1. d4 Sc6 2. Kd2 Se5 3. dxe5 Sf6 4. exf6 g5 5. fxe7 Lh6 6. exd8 0-0 7. Ke3 g4+ 8. f4 gxf3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to either minor officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sk), En passant
Genre: Retro
Computer test: HJ: with wSd8 C+ Stelvio 1.0
FEN: r1bP1rk1/pppp1p1p/7b/8/8/4Kp2/PPP1P1PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
22 - P1408365
Andrew Buchanan
5 Problemas 36, p. 1189, 10/2021
P1408365
(15+14) C+
PG in 8.0
1. f4 e6 2. f5 Lc5 3. f6 Se7 4. fxe7 Lb6 5. exd8 c5 6. Kf2 0-0 7. Ke3 c4+ 8. d4 cxd3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to either minor officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sk), En passant
Genre: Retro
Computer test: HJ: with wSd8 C+ Stelvio 1.0
FEN: rnbP1rk1/pp1p1ppp/1b2p3/8/8/3pK3/PPP1P1PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
23 - P1408366
Andrew Buchanan
6 Problemas 36, p. 1189, 10/2021
P1408366
(15+14) C+
PG in 8.0
1. f4 d5 2. f5 Ld7 3. f6 Lc6 4. fxe7 Sd7 5. exf8 Dg5 6. Kf2 0-0-0 7. Kf3 d4+ 8. e4 dxe3ep+
play all play one stop play next play all
Objective: record achievement of task. Promotion can be to either minor officer, but prefer to keep the "stem cell" to avoid arbitrary choice of non-standard material.
more ...
comment
Keywords: Unique Proof Game, Dummy Pawn (in diagram), Valladao Task, Golden Age (Dummy Pawn), Castling (sg), En passant
Genre: Retro
Computer test: HJ: with wSf8, C+ Stelvio 1.0
FEN: 2kr1Pnr/pppn1ppp/2b5/6q1/8/4pK2/PPPP2PP/RNBQ1BNR
Input: A.Buchanan, 2023-03-19
Last update: A.Buchanan, 2023-08-04 more...
24 - P1408483
Andrew Buchanan
P522 StrateGems 96 10/2021
after Cedric Lytton
P1408483
(12+13) C+
PG in 16.5
1. Sf3 d5 2. Tg1 d4 3. Sxd4 a5 4. Sb3 Dxd2+ 5. Lxd2 Ta6 6. Dc1 Te6 7. Kd1 Txe2 8. Le1 Te4 9. S1d2 Ta4 10. Lc4 Txa2 11. Sf1 Ta4 12. Ta3 Tb4 13. Sa1 a4 14. La2 Th4 15. Lb1 Txh2 16. Th3 Th1 17. Thxh1
play all play one stop play next play all
Henrik Juel: 1.Sf3 d5 2.Rg1 d4 3.Sxd4 a5 4.Sb3 Qxd2+ 5.Bxd2 Ra6 6.Qc1 Re6 7.Kd1
Rxe2 8.Be1 Re4 9.S1d2 Ra4 10.Bc4 Rxa2 11.Sf1 Ra4 12.Ra3 Rb4 13.Sa1 a4 14.Ba2 Rh4
15.Bb1 Rxh2 16.Rh3 Rh1 17.Rhxh1
The final position shows the white officers shifted one square to the left, cyclically
(actually the knights also shift places, so Sa1 is [Sg1], and the bishops must keep their square color, of course) (2023-03-24)
Henrik Juel: Stelvio 1.0 found the solution in 55 minutes, and was stopped after an hour
Cedric's problem P1389511 is C+ Euclide 1.01 in 6:22 hours:minutes (2023-03-24)
A.Buchanan: Reto not only has his new engine, he has some heavy dedicated computing power. Relieved that he identified that this one is sound, with its two triple cyclic shifts: BQK & RRN plus platzwechsel BN (2023-03-25)
comment
Keywords: Unique Proof Game
Genre: Retro
Computer test: C+ Stelvio v1.0 389m strategies found in total, 7.27m of them played (rest discarded because of analysis). Total 24.7 billion moves played.
FEN: 1nb1kbnr/1pp1pppp/8/8/p7/8/1PP2PP1/NBQKBNRR
Input: A.Buchanan, 2023-03-24
Last update: A.Buchanan, 2023-03-25 more...
25 - P1408486
Andrew Buchanan
R2 Phénix 321, p. 12538, 08/2021
P1408486
(12+12) C+
PG in 9.0
1. f4 c5 2. f5 c4 3. f6 c3 4. fxg7 cxb2 5. gxh8=S bxa1=D 6. Sg6 Dg7 7. Sxf8 Dxg2 8. Lxg2 Kxf8 9. Lf1 Ke8
play all play one stop play next play all
Henrik Juel: ... actually 1:04 h:m
C+ Popeye 4.61, in 1:15 h:m
I guessed that this type of problem was tested most rapidly by a plain total search, like Popeye and Jacobi
Smart PG solvers, like Natch, Euclide, and Stelvio, cut down parts of the search tree by reasoning like a human solver; but here the cutting down is largely wasted, because there are few clues
Conclusion:
Solve this type of problem by hand and let somebody else test it... (2023-03-24)
A.Buchanan: Yes: human solving for this kind of problem is suggestive rather than deductive. For example, the "footprints in the snow" on the queenside: it looks as if sBc may have captured on b2 & a1, then went away after promotion. That suggests that maybe wBf captured g2 & f8/8. Got to explain two more holes: g2 & h8/f8. Pronkin doesn't seem like a possibility, so capturer switchback seems the most likely. But how to *prove* this is the only solution? This problem was composed for the RIFACE solving competition, and was one of the easier ones. (2023-04-26)
more ...
comment
Keywords: Unique Proof Game, Homebase (2)
Genre: Retro
Computer test: C+, Jacobi v0.7.5 C+ Popeye 4.61, in 1:15 h:m C+ Stelvio 1.0 also, in 1:04 h:m c
FEN: rnbqk1n1/pp1ppp1p/8/8/8/8/P1PPP2P/1NBQKBNR
Input: A.Buchanan, 2023-03-24
Last update: A.Buchanan, 2023-04-26 more...
26 - P1408845
Andrew Buchanan
Phénix 11/2021
after J-F. Baudoin & J-C. Gandy
P1408845
(9+13)
-1s -1w -1s, dann h#1
R: 1. ... h2-h1=S+ 2. a7-a8=L Kc8-d8 dann 1. h1=T a8=D#
play all play one stop play next play all
AB: Mario was kind enough to check this 2-Jul-2021. I hope it's ok if I quote his email:

The trick with the light-squared black Bishop is fine, but makes things too complicated for rawbats. It will happily retract e.g. R: 1. ... h2-h1=S+ 2. Lb7-a8 Ke7xDd8, dann 1. Kd6 Df6# without noticing that the retractions lead to a conflict on the g-file: either wPh2 captured the original Bishop c8 on the g-file, then bPg7 was not available a a capture object for the remaining white pawn captures, or wPh2 captured the original bPg7 on the g-file, then the original light-squared black bishop c8 was not available a capture object for the remaining white pawn captures f2xe3xd4 (both on dark squares).
So brain-checking your retractor and your logical argumentation I found no defects, and I think the problem is sound now
corrects P0003922
more ...
comment
Keywords: Help retractor, Allumwandlung
Genre: Retro, h#
FEN: B2k4/2pp4/8/8/1PPP4/1rpP2PN/1pppPK2/nrbq3n
Input: A.Buchanan, 2023-04-13
Last update: A.Buchanan, 2024-01-21 more...
27 - P1409841
Andrew Buchanan
1 Phénix 331, p. 12922, 06/2022
after A.Lubusov
P1409841
(15+6) C+
h#2* (AP)
1. ... e6 2. 0-0? Lxh7# (castling rights lost)
1. ... Txh7 2. Tf8 Te7#

1. cxb3ep Txh7 2. Tf8? Te7# (ep needs AP justification)
1. cxb3ep e6 2. 0-0! Lxh7#
play all play one stop play next play all
White pawns have captured 9 times right-to-left, accounting for all but one missing Black unit. So by parity, there were no other pawn captures by White. So wBb never left that file, and Black cannot have just played Bb3xa2 behind it. sBa was waylaid on a-file by an officer.

So if Black moved last, it must have been Ke8 or Th8, and Black has lost castling rights.

On the other hand, if White moved last, then Black needs a tempo move. The only possible one is ep capture. (1. Tg8+? is check.) But the ep capture is only legal if Black retains castling rights, so Black's second move must indeed be 0-0 for A Posteriori justification.

In this case, last moves were R: 1. b2-b4 b3xDa2 & e.g. 2. Le3-d4,~ b4-b3 3. d4xSc5,~ Sa6-c5,~ with many ways for White to release Black.
Corrects P0000615.
more ...
comment
Keywords: a posteriori (AP), RIFACE Retro Solving Tourney (2022), En passant as key, Castling (sk), Tempo Move, waylaid (sBa)
Genre: h#, Retro
Computer test: HC+ Popeye v4.87 & simple retro thinking
FEN: 4k2r/1N1p3p/3P4/1PPPP3/1PpBBP2/P1N3K1/p7/R6R
Input: A.Buchanan, 2023-05-20
Last update: A.Buchanan, 2023-09-11 more...
28 - P1409850
Andrew Buchanan
H1327 Problem Paradise 97, p. 11, 01-03/2022
P1409850
(3+13) C+
h#3
b) sSb5<->sBa7
a) 1. ... axb7 2. Kc7 Kd5 3. Kd8 b8=D#
b) 1. Tc7 e7 2. Kd7 Kd5 3. Kc8 e8=D#
play all play one stop play next play all
Unique set play retro try in the retro twin s). 1.Kc7 axb7 2.Kd8 b8=D#. Zero set play in b).
All pieces are necessary for soundness in at least one twin except for sBa4 ("the manager").
First publication had typo in stipulation
Henrik Juel: If you disregard retro considerations and blindly test with Popeye 4.61, you get lots of cooks in part a) and 1.Re7-c7 e6-e7 2.Kc6-d7 Ke4-d5 3.Kd7-c8 e7-e8=Q #
in part b) (2023-05-20)
Henrik Juel: Part b) is OK, because last move could be Kd4-e4, and a normal h#3 ensues
But in part a) White (not Black as intimated by the Keyword) has no last move, and the stipulation changes to h#2.5 with the solution 1...a6*b7 2.Kc6-c7 Ke4-d5 3.Kc7-d8 b7-b8=Q #
Nice symbol problem (2023-05-20)
more ...
comment
Keywords: No legal last move for White, Character problem (PP)
Genre: h#, Retro
Computer test: HC+ Popeye 4.61 and simple analysis
FEN: 8/pp2rp2/P1k1P1p1/pn2nr2/p3K3/q3b3/8/8
Reprints: OP015 The Hopper Magazine I02 25/06/2022
Input: A.Buchanan, 2023-05-20
Last update: A.Buchanan, 2023-12-06 more...
29 - P1410861
James Malcom
Siegfried Hornecker
Joaquim Crusats
Andrew Buchanan

12 MatPlus.net Forum 25/06/2023
P1410861
(16+4)
What is curious about this position?

Fewest Black pieces requiring all 16 White pieces in a legal checkmate position

https://matplus.net/start.php?px=1689032781&app=forum&act=posts&fid=gen&tid=3043
A.Buchanan: Mu-Tsun Tsai suggests that for construction problems such as this, the stipulation might be "What is curious about this position?" (2023-07-13)
James Malcom: That feels apt. (2023-07-14)
more ...
comment
Keywords: Superseded by (P1410903)
Genre: Retro, Fairies
FEN: B1Qr2RK/3P2N1/1P4RB/1rP5/4kP2/PPP5/q2P4/2N5
Input: James Malcom, 2023-07-11
Last update: A.Buchanan, 2023-07-27 more...
30 - P1411151
Andrew Buchanan
SS101 The Hopper Magazine I04 13/07/2023
P1411151
(12+11) C+
PG in 8.0
1. b4 g5 2. b5 g4 3. b6 g3 4. bxc7 gxh2 5. cxb8=T hxg1=D 6. Txb7 Dxg2 7. Txd7 Dd5 8. Txd8+ Dxd8
play all play one stop play next play all
more ...
comment
Keywords: Homebase, Unique Proof Game
Genre: Retro
Computer test: C+, Jacobi v0.7.5
FEN: r1bqkbnr/p3pp1p/8/8/8/8/P1PPPP2/RNBQKB1R
Input: Miguel Ambrona, 2023-07-25
Last update: A.Buchanan, 2023-07-27 more...
31 - P1411669
Andrew Buchanan
idee & form 159, p. 5394, 07/2023
after Sam Loyd
P1411669
(15+11) C+
PG in 12.0
1. e4 a6 2. Lxa6 h5 3. Lxb7 Ta6 4. h4 Tah6 5. Th3 f6 6. Tc3 Kf7 7. Txc7 Sc6 8. Lxc6 La6 9. d3 Lxd3 10. e5 Lh7 11. Dxd7 Kg6 12. De6 Dd1+ DP
play all play one stop play next play all
Shortest PG to DP. Previous record was various massacres in 16.5 moves: PROBID IN 'P0005395; P0005400; P0005401; P1013074'
more ...
comment
Keywords: Unique Proof Game, Dead Position (game end)
Genre: Retro
Computer test: C+ Stelvio 1.4 (it is not necessary to test 11.0 moves)
FEN: 5bnr/2R1p1pb/2B1Qpkr/4P2p/7P/8/PPP2PP1/RNBqK1N1
Input: A.Buchanan, 2023-08-09
Last update: A.Buchanan, 2023-08-10 more...
32 - P1411670
Andrew Buchanan
idee & form 159, p. 5394, 07/2023
after Sam Loyd
P1411670
(15+10) C+
PG in 13.5
1. e4 a6 2. Lxa6 h5 3. Lxb7 Ta6 4. h4 Tah6 5. Th3 f6 6. Tc3 Kf7 7. Txc7 Sc6 8. Lxc6 La6 9. d3 Lxd3 10. e5 Lh7 11. Dxd7 Kg6 12. De6 Dd4 13. Ke2 De3+ 14. Lxe3 = pat
Try 12. ... Dd3? 13. Le3 De2+ DP as 14. Kxe2 (&Sxe2) = pat
play all play one stop play next play all
Shortest known PG where DP provides dual removal. Previous record was massacre P1281143 15.5 moves
Henrik Juel: for completeness: the try fails as 14.Kxe2,Sxe2 = pat (2023-08-09)
more ...
comment
Keywords: Unique Proof Game, Dead Position (dual elim)
Genre: Retro
Computer test: HC+ Stelvio 1.4 finds no solutions in 13.0 moves and a slightly dualistic solution in 13.5 moves, use manual DP logic to eliminate this try.
FEN: 5bnr/2R1p1pb/2B1Qpkr/4P2p/7P/4B3/PPP1KPP1/RN4N1
Reprints: www.chess.com 18/12/2023
Input: A.Buchanan, 2023-08-09
Last update: A.Buchanan, 2023-12-18 more...
33 - P1413906
Andrew Buchanan
3 Problemas 44, p. 1456, 10/2023
after Gyula Bebesi
P1413906
(11+14) C+
h#2
1. axb3ep bxc6+ 2. b5 cxb6ep#
1. exd3ep Dxg8+ 2. d5 cxd6ep#
play all play one stop play next play all
Wh captures axb, XxLc1.
Bl captures cxb/dxc, hxg, gxh/f and either fxe or wBe is waylaid. So the position is legal, with Wh last move being pawn double hop. In particular wKf6-e5 was not the last move

PRA, last move was either b2-b4 or d2-d4. So there is "one solution with two parts".
See P0003365 (cooked) & P1411659 (fixably cooked but non-standard thematic material).
This new version has an obvious promoted unit (non-thematic), but Joaquim Crusats (a noted constructor) could not find any way to do better
Ladislav Packa: Mr. Bebesi's first name is Gyula (not Gyulia). It is the Hungarian version of the name Julius. (2023-12-05)
A.Buchanan: Thanks - edited (2023-12-06)
more ...
comment
Keywords: Partial Retro Analysis (PRA), Obvious promotion (l), En passant as key (2), En passant as mating move
Genre: h#, Retro
Computer test: HC+ Popeye 4.61
FEN: 3rn1bQ/1p1p2PR/B1r3pP/1PP1K2n/pPkPp3/b1p5/N7/2q5
Reprints: SuperProblem (Website) 06/12/2023
Input: A.Buchanan, 2023-12-04
Last update: A.Buchanan, 2023-12-06 more...
34 - P1413923
Andrew Buchanan
R611 The Problemist 07/2023
P1413923
(15+11)
Proof Game in 12.5
Game over!

A long-standing question (since a problem by Michel Caillaud P1004030, and also one by Guus Rul) asks how the Draw by Triple Repetition (3Rep) convention interacts with the Dead Position rule (DP). This is not an issue over the board, since 3Rep must be claimed. Miguel Ambrona proposed that for retro problems, DP rule has visibility of any looming 3Rep or 50M draw, while for purely forward problems, e.g. help dead position (HDP), it does not. This distinction works extremely well: it enables problems such as Michel's and this new one, while allowing us to eliminate a class of cooks which would be ubiquitous in longer HDP problems. So the HDP design space does not hit an effective ceiling at 4.0 moves. The concept of "retro problem" is already used in Codex Articles 17 & 17A for 50 move rule & DP, so is not new.
more ...
comment
Keywords: Unique Proof Game, Constrained problem, Draw by repetition, Castling, En passant
Genre: Retro
FEN: 2Q1kb1r/1pp1ppp1/3q3p/2Pp1R2/8/1P6/1P1P1PPP/1NB1KBNR
Reprints: www.chess.com 18/12/2023
Input: A.Buchanan, 2023-12-05
Last update: A.Buchanan, 2023-12-18 more...
35 - P1413924
Johannes Jacob Burbach
Alain C. White
Andrew Buchanan

PDB Website 05/12/2023
JJB & ACW, version AB
P1413924
(4+6) C+
h#2
b) -sBg6h7
a) 1. Ta5 Kd1 2. Ta2 Kc2# (not 1.Ta7?etc Lxc3 because White may not castle)
b) 1. Ta7 Lxc3 2. Ta2 0-0# (last move could be 0.h7-h8=L)
play all play one stop play next play all
See P0003666
A.Buchanan: Apart from having removed wBe2/sBe3, I don't think this is an improvement. In the original, sBh6 gave and took. The version is more economical but there's two pawns difference between the twins. (2023-12-06)
more ...
comment
Keywords: Cant Castler, Castling (wk), Remove pieces
Genre: h#, Retro
Computer test: HC+ Popeye v4.87 + trivial retro logic
FEN: 7B/6rp/6p1/7r/8/2p5/1P6/k3K2R
Input: A.Buchanan, 2023-12-05
Last update: A.Buchanan, 2023-12-05 more...
36 - P1414063
Andrew Buchanan
The Puzzling Side of Chess 228 31/10/2023
P1414063
(14+2)
Dead position, with check, maximizing the number of legal but unplayable moves.

20 legal but unplayable moves.
Black just played c6xd5+ or exd5+, not d6-d5? which would have ended the game in prior dead position.
Henrik Juel: The position is displayed by clicking on one of the five animation symbols and then moving the cursor (2023-12-14)
Henrik Juel: ... and then moving the cursor up (2023-12-14)
A.Buchanan: I think the phrase "legal but unplayable" is happier than "impossible", so I will use the former (2023-12-14)
A.Buchanan: Have reverted to the mode in which PDB shows the diagram directly, rather than having to click animation. (2023-12-16)
more ...
comment
Keywords: Construction record, Minimal, Dead Position, Type C, Non-standard material (TTLSSSS)
Genre: Retro, Mathematics
FEN: B5Bk/2NRN3/1N3N2/R2p2R1/2KR1N2/4N3/6Q1/8
Input: A.Buchanan, 2023-12-14
Last update: A.Buchanan, 2023-12-16 more...
37 - P1415606
Maurice Jago
Andrew Buchanan

PDB Website 07/03/2024
MJ, correction AB
corrects 8202v Die Schwalbe, p.148, 10/1980
P1415606
(8+15)
h#2
b) sBb4->b5
Supersedes P0003659.
"The noted Cornish problemist, Dr. Maurice Jago was most prolific during the war when he was a lieutenant in the Royal Army Medical Corps. He became increasingly interested in the more flamboyant and unusual kinds of positions and problems." (www.keverellchess.com, now closed)
Yuri Bilokin: perhaps such a version does not harm the author's intention –wNa7, -wNa8, -wBb8, -wPd3, -bRc8, -bPc7, -bPe7 8/8/1Pqp4/2bb4/1p6/n1p2rP1/1PP1P2k/R3KQ1n (8+12) h#2 b) bPb4-b5 (2024-03-10)
Yuri Bilokin: slip of the pen -wNa7, -wNa8, -wBb8, -wPd3, -bRc8, -bPc7, -bPe7, -bPa4, -bPg6 8/8/1Pqp4/2bb4/1p6/n1p2rP1/1PP1P2k/R3KQ1n (8+10) h#2 b) bPb4-b5 (2024-03-10)
A.Buchanan: Hi Yuri thanks yes it’s more than intention here. In b need to ensure that White can’t have just played axb6, fxg3 or g2-g3, in order to eliminate the castling try: the extra pieces are all to ensure this (2024-03-11)
Yuri Bilokin: Hi Andrew. I apologize, I didn't go there, although the white horse on the a8 square still bothers me. (2024-03-11)
A.Buchanan: WP cap: axb BP caps: fxexdxc. bPh must have promoted, so either bPh3xg2-g1= or wPh was waylaid. In any case, all captures are accounted for. wPf promoted. Easy to see that White cannot have just played g2-g3 or f2xg3 or d2-d3 or axb6. So must have bPb4 rather than b5, allowing for White to have just played Sb5-a7 or b5-b6. If any of the "retro-dressing" White pieces e.g. Sa8 are removed, then White might have just played g2-g3 or d2-d3. At least the retro-dressing units have no possible last move (& wSa8 wBb8 have not just promoted), so there is some craft to their deployment. (2024-03-11)
A.Buchanan: bPg6 blocks a cook so must stay there, but can shift bPe7 to d7 (allowing the removal of wSa8 or wBb8) or to b3/b7 (allowing the removal of all three White officers: wSa7a8 & wBb8.) Maybe that's worth doing? (2024-03-11)
Yuri Bilokin: Thank you for the detailed analysis. Perhaps my poor view will allow you to get an optimal starting position. (2024-03-11)
Henrik Juel: a) 1.Sh1-f2 Qf1*f2 + 2.Kh2-h1 0-0-0 #
b 1.Sa3-b1 Ra1*a4 2.Sh1*g3 Ra4-h4 # (2024-03-11)
Henrik Juel: C+ Popeye 4.61 and analysis (2024-03-11)
A.Buchanan: I had wanted to keep to the spirit of P0003659, in which may be the author wanted to have a bunch of White retro-dressing that could not retract. But going back to the first version P0003659, the White position is much cleaner. So following Yuri being bothered by a horse, I am going to change the diagram here from NBr5/N1p1p3/1Pqp2p1/2bb4/pp6/n1pP1rP1/1PP1P2k/R3KQ1n by removing 4 white units. Hope this is agreeable to all (2024-03-13)
more ...
comment
Keywords: Cant Castler, Castling (wg)
Genre: h#, Retro
FEN: 8/rpp2p2/1Pqp4/2bb4/pp6/n1p2rP1/1PP1P2k/R3KQ1n
Input: A.Buchanan, 2024-03-06
Last update: A.Buchanan, 2024-03-13 more...
Show statistic for complete result. Show search result faster by using ids.

https://pdb.dieschwalbe.de/search.jsp?expression=COMMENTDATE%3E%3D20220810+AND+G%3D%27Retro%27+AND+NOT+K%3D%27Cross-capture%27+AND+A%3D%27Buchanan%2C+Andrew%27

The problems of this query have been registered by the following contributors:

Gerd Wilts (1)
A.Buchanan (31)
James Malcom (2)
Gunter Jordan (2)
Miguel Ambrona (1)