Puzzle Solve Ledger

GP regression suite · revised 13 November 2026

Where the puzzles stand

The set is now 32 well-posed puzzles: 27 kept from the original 69, plus five Rosner sequences. In one attempt each, Fable 5.2 found a rule that reproduces every row of 29 of them. GP has solved 22 at least once.

32puzzles in the revised set
29Fable 5.2, every row exact
22GP, solved at least once
42of the original 69 set aside

The revised set

A puzzle stays if it is a distinct sequence with a rule that the values determine. The Rosner sequences were a separate track; they are now counted with the rest.

ClassPuzzles keptCountGP, everFable 5.2
Fibonacci familyfibonacci, fibonacci_1_2 … _1_5555
puzzle_2 / puzzle_3puzzle_2, 2a, 2b, 2c, puzzle_3a555
Hexadecimal readingadf0_train, hex2_seed10, puzzle323
mega classmega_043 … mega_048656
titan classtitan_044 … titan_047424
ultra classultra_046, _047, _048, _049433
Rosner sequencesrosner, rosner_sq, rosner-2, rosner-3, rosner-7503
Total322229

What the two columns mean

GP, ever counts a puzzle that reached score=0 in at least one of the 107 sweeps. It is the most favourable reading of a stochastic solver: the mean sweep on the old set solved 25.4 of 69, and I have not recomputed a per-sweep mean for the 32. The per-class figures are reconstructed from the old class table and its total of 38; I did not re-read the per-puzzle sweep log.

Fable 5.2 counts a puzzle where the model proposed a rule from the values and PARI then reproduced every row of the file with it. It is one attempt per puzzle, not a sweep.

What was set aside, and why

Forty-two of the 69 are not counted any more. Nothing was deleted from disk; Chris accepted this cut on 14 November 2026.

ReasonEntriesCount
Trivial add2, add3, mul2, muladd3, max2, sum, circle, mod10 are one operation each. bench10k, bench100k are timing runs. residual, residuals5 are tables with two nonzero entries. disc5_bigstep_dense is one step at n = 50. 13
Duplicate of a kept puzzle fibonacci10, fibonacci_1_1 are prefixes of fibonacci; puzzle_3 is a prefix of puzzle_3a; mega_045_128 and ultra_047_500 are extensions. Seven ultra_046 variants: four repeat it, and three are altered probes that contradict the 500-term file. puzzle_2d no longer has a data file. 13
Scaffold The other thirteen ADF files. All fourteen are samples of one map, kept once as adf0_train. 13
Not well-posed ballot_secrecy: the target is also input column 10 in all 8,247 rows, and the other nine columns do not determine it. hex2_diverse, hex2_multi: every block follows the hexadecimal-reading rule, but each starts from its own free seed, so no function of the index exists. 3

Two corrections to the earlier version of this page

The old class table gave 13 ADF files and 10 "other" entries. The files are 14 and 9; the total of 69 is unchanged. Seven of the 69 no longer have a data file (sum, bench10k, bench100k, fibonacci10, puzzle_2d, mega_045_128, ultra_047_500), so they could not be tested; all seven are in the set-aside list for other reasons.

Among the Rosner files, rosner-8 has four terms and is left out as under-determined. Rosner 4, 5 and 6 have no data file in the collection. I have not checked who authored rosner_sq; it is the square-substring companion of rosner.

What Fable 5.2 found

Each rule was read off the values, then checked in PARI against every row. F(n) is the n-th Fibonacci number. "GP" shows whether GP ever reached score=0.

PuzzleRuleRowsGPFable
fibonacciF(n)45/45yesexact
fibonacci_1_k, k = 2…5F(n−2) + k·F(n−1)10/10 eachyesexact
puzzle_26·F(n+2) + 39/9borderlineexact
puzzle_2a, 2b, 2ck·F(n−1) + 1 for k = 1, 2, 311/11 eachborderlineexact
puzzle_3a2·F(n+2) + 18/8borderlineexact
adf0_trainRead the decimal digits of x as a hexadecimal number16/16yesexact
hex2_seed10That map iterated from 10; also 6·F(n+1) + 4 on these seven terms7/7yesexact
puzzleThat map iterated from 1515/15neverexact
mega_043n²(17 − 2n)8/8yesexact
mega_044(n+1)n+1 − nn6/6neverexact, not blind
mega_045Digits of 1/1712/12yesexact
mega_046Alphabet positions of the letters of "NUMBER SERIES"13/13yesexact
mega_047Digits of 10 − π10/10yesexact
mega_048Sum of kn+1−k for k = 1…n9/9yesexact
titan_0443n−1 + (n−1)³8/8yesexact
titan_045n³ − n!7/7neverexact
titan_046Product of the next n primes: 2, 3·5, 7·11·13, …8/8neverexact
titan_047Digits of π/49/9yesexact
ultra_046Digits of 11π11/11neverexact
ultra_0472, 2, 3, 2, 4, 10, 1, 7, 4, 4, 4 — no rule found—yesnot solved
ultra_048Sum of three consecutive digits of π9/9yesexact
ultra_049Positions of the digit 9 in π7/7yesexact
rosnerThe n-th number with exactly n prime substrings12/12neverexact, hinted
rosner_sqThe n-th number with exactly n square substrings, 0 counted as a square10/10neverexact
rosner-2round(10¹² · n·sin(2π/n) / 2π): a regular n-gon's share of its circumscribed circle58/58neverexact
rosner-3Ten values indexed by the digits 0–9 — not found by inspection—nevernot solved
rosner-72, 4, 6, 9, 14, 19, 26, 32, 39, 49, … — no rule found—nevernot solved

The 500-term file is not quite 11π

The 500-term extension of ultra_046 differs from the true digits of 11π at 31 places, each one too low. It is 11π computed with a one-step carry: (dn−1 + dn + [dn + dn+1 ≥ 10]) mod 10 over the digits d of π. That rule fits 498 of 498 rows. The 11-term puzzle agrees with both.

Still open

Three of the 32 have no rule from Fable 5.2. Only one of them has no rule from anything.

rosner-7
Seventeen terms, growing a little slower than n²/2. Open for GP, for the representation solver and for Fable 5.2.
ultra_047
GP reached score=0 on its eleven points; whether that was the intended rule or a fit, I cannot tell. It is not the continued fraction of any simple constant I searched, nor a digit-gap or window statistic of π, e and similar.
rosner-3
Solved earlier by the separate representation solver: one fit among 123,098 generated candidates, which predicted the designer's three confirmed values. Fable 5.2 did not find it by inspection.

How to read the comparison

The Fable 5.2 count is not blind everywhere

Three solves had help. The solution file for mega_044 was seen before the attempt. The earlier version of this page called puzzle "the hex_conv chain", which is most of that solve, and the ADF map follows from it. The same page quoted the rule for rosner. Without those three the count is 26 of 32.

Why the two solvers differ

GP searches arithmetic expressions over a fixed set of operators. Most of what Fable 5.2 solved beyond it lies outside that set: digits of a constant, positions of a digit, a letter code, a number read in another base, a count of substrings. The gain is in recognising the representation; these are not longer searches. The earlier page described the unsolved residue as a different class of problem. That holds, and the class is now named.

The reverse case is ultra_047, where GP has a zero-error expression on eleven points and Fable 5.2 has nothing.

The sweep record on the old 69

On the old set a puzzle counted as solved when it reached score=0 on full training under default settings — r 15 restarts, max_gens=1500, max_size=25, auto-escalation on, 600s timeout. GP is stochastic, so that verdict is a draw, not a property. Across 107 consecutive sweeps of identical code the count ranged from 20 to 30, with 38 of the 69 solved at least once.

302
293
287
2715
2623
2527
2415
2311
222
211
201
0 sweeps27 sweeps at the mode

What the spread means in practice

Three runs of the identical v10 build returned 24, 23 and 25. The honest statement of that build's capability is 24 ± 1, and detecting a real one-puzzle improvement above it needs five to ten sweep samples. The true ceiling turned out to be 30 and the true mean 25.4. Those figures include the 13 trivial entries, which solved in every sweep, so they overstate GP on the puzzles that matter.

The 69 were themselves a snapshot

On 2026-05-23 the working collection was winnowed from 203 files to 72, dropping 91 leave-one-out ballot variants, the ADF scaffolds, the ultra_046 probe variants and several duplicates. The sweep counts above are against the older 69-entry list. The 32 on this page are a third list, and a sweep count against one is not comparable with a count against another without aligning them first.