# Learn from strong boards > Most attacks on Eternity II search from first principles. A distinct family does the opposite: it mines the corpus of boards people have already found for structure, then feeds that structure back into the search. Position priors, learned move-ordering, anti-pattern mining, record decoding, and the failure mode where a learned signal collapses. - Canonical page (with interactive figures/demos): https://eternity2.dev/research/build/learning/ - Updated: 2026-07-16 --- Every other family on this shelf searches from first principles: a backtracker digs, a beam builds, a local search polishes, each reasoning only from the rules of the puzzle and the board in front of it. This family does something different. It takes the corpus of strong boards people have already found, reads it for structure, and feeds that structure back into a search as a bias. It is closer to imitation learning than to search design: the question is not "what is a good move" from first principles but "what did the boards that scored well tend to do, and can that be reused." The pages below go technique by technique. Each is genuinely its own method, so they do not share a shape the way the local-search polishers do: a position prior, a learned move-ranking, an anti-pattern miner, and a witness replay share a thesis but not a mechanism. For the whole territory at once, start with [a map of every known approach](/research/build/approaches-map). For the runnable experiments that embody these techniques, with their boards and numbers, see the [learning-from-boards experiments](/research/lab/experiments/raphael-anjou/learning). ## The thesis, and its limit A learned signal helps when it captures real, transferable structure: something true of good boards that a from-scratch search would otherwise have to rediscover by luck. Where each piece tends to sit, which pieces like to touch, which scarce demand a rare piece is the only one that can serve. Wired into a search as a gentle bias, that structure reliably carries a build to the top of its own range. The limit is the part that makes this research rather than a bag of tricks. The corpus these signals are learned from is itself sub-perfect: every board in it is stuck somewhere below 480. So a signal mined from the corpus encodes the community's *ceiling* as much as its wisdom, and a signal that merely re-encodes the plateau every strong board is already caught on raises nothing. Push a learned prior from a tiebreak into the objective and the search collapses, because it starts trading the edge in front of it against a statistical hunch. The plain through-line of this whole family: learning from strong boards helps you reach the plateau fast and reliably, but it does not, on its own, get you past it. The ceiling is the [rigidity wall](/research/why/rigidity-wall), and no amount of corpus mining moves it. ## The techniques - **[Corpus priors](/research/build/learning/corpus-priors)** are the simplest form: count where each piece sits in strong boards, or how often a piece serves a scarce demand, and use the count as a tiebreak in construction. The [PRIOR](/research/lab/experiments/raphael-anjou/learning/prior) and [LODESTONE](/research/lab/experiments/raphael-anjou/learning/lodestone) experiments. - **[Learned move-ordering](/research/build/learning/learned-value-ordering)** ranks candidate placements by several learned signals at once, and lets them vote, so no single hunch marches the search into the same dead end. The [KEYRING](/research/lab/experiments/raphael-anjou/learning/keyring) experiment. - **[Anti-pattern mining](/research/build/learning/anti-pattern-mining)** is the subtler idea: not every agreement across strong boards is good. Separate the real structure from the shared trap, and attack the trap. The [PALIMPSEST](/research/lab/experiments/raphael-anjou/learning/palimpsest) experiment, which reached this project's best board. - **[Decoding records](/research/build/learning/decoding-records)** reconstructs a known record board exactly, piece for piece, to recover the ingredient an ordinary search was missing. Reproduction as proof. The [REPLAY](/research/lab/experiments/raphael-anjou/learning/replay) experiment. - **[When learning collapses](/research/build/learning/when-learning-collapses)** is the failure-mode capstone: exactly when a learned signal stops helping, why over-trusting it wrecks the search, and why none of these methods raise the ceiling. It sets the limit for the whole section: learned signals reach the plateau faster, but none of them lift it. ## Pages in this section - [Corpus priors](https://eternity2.dev/research/build/learning/corpus-priors) — The simplest way to learn from strong boards: count where each piece tends to sit, or how often it serves a scarce demand, and use that count as a gentle tiebreak in construction. It has to stay a tiebreak; the moment it becomes part of the objective it collapses the search. - [Learned move-ordering](https://eternity2.dev/research/build/learning/learned-value-ordering) — When several pieces fit, which do you place next? Instead of one rule of thumb, carry several signals learned from strong boards and let them vote. Voting keeps the search from over-trusting any one hunch and marching into the same dead end. - [Anti-pattern mining](https://eternity2.dev/research/build/learning/anti-pattern-mining) — The subtle idea in learning from strong boards: not every agreement between them is good. Some shared placements are real structure; some are a shared trap that caps every search just short of the top. Separate the two, and attack the trap. - [Decoding records](https://eternity2.dev/research/build/learning/decoding-records) — The most literal way to learn from a strong board: rebuild it exactly, piece for piece, until your search can reproduce it. What the reconstruction forces you to add is the ingredient your search was missing, and the reproduction is the proof. - [When learning collapses](https://eternity2.dev/research/build/learning/when-learning-collapses) — The sobering half of learning from strong boards. A learned signal reaches the top of a search's own range reliably, and then stops. Over-trust it and the search collapses; even used perfectly it does not raise the ceiling, because the ceiling is not a thing the corpus knows. ## Related - [A map of every known approach](https://eternity2.dev/research/build/approaches-map) — The survey the community keeps asking for and never finds: every family of attack tried on Eternity II, what each one actually reached, where it walls out, and a link to the deep page. One organising insight runs through all of them. - [The techniques](https://eternity2.dev/research/build/techniques) — The technique shelf: the algorithms and pruning ideas that recur in every serious Eternity II solver, each with what it is, what it costs, and what it actually bought when measured on this puzzle. - [Learning from strong boards](https://eternity2.dev/research/lab/experiments/raphael-anjou/learning) — A study in five experiments of one idea: instead of searching Eternity II from first principles, mine the corpus of strong boards already found for structure and feed it back into a search. A position prior, a learned move-vote, a scarce-demand compass, an anti-pattern miner, and a record decode, ordered from the simplest signal to the subtlest, and the one wall all five reach.