A neuro-symbolic post-training pipeline lets a 4B transformer learn cubing heuristics that reach pass@5 of 53 on 100 SAT competition instances, matching the strongest symbolic baseline.
International Conference on Theory and Applications of Satisfiability Testing (SAT) , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning How to Cube
A neuro-symbolic post-training pipeline lets a 4B transformer learn cubing heuristics that reach pass@5 of 53 on 100 SAT competition instances, matching the strongest symbolic baseline.