Foundational MIP embeddings transfer directly to SAT for unsupervised clustering and distribution identification without architectural changes or supervised training.
Enhancing sat solvers with glue variable predictions
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
-
Transfer Learning from Foundational Optimization Embeddings to Unsupervised SAT Representations
Foundational MIP embeddings transfer directly to SAT for unsupervised clustering and distribution identification without architectural changes or supervised training.