Research map / Graph learning / Graph algorithms and clustering
Learning a SAT Solver from Single-Bit Supervision
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Run NeuroSAT for four times more iterations than during training | NeuroSAT on SR(200) · SR(200), sat problems | solved problems: under 10% -> 25% | Helped |
| Train the same architecture on problems containing small unsat cores | NeuroSAT architecture, yielding NeuroUNSAT · SRC(40, u) | test accuracy: 100% | Helped |
| Cluster literal embeddings to decode satisfying assignments | NeuroSAT · SR(40), sat problems | solved problems: 70% | Helped |
| Run NeuroSAT for 512 iterations on encoded problems from other domains | NeuroSAT · Encoded graph coloring, clique detection, dominating set, and vertex cover problems | decoded solutions: 85% | Helped |
Closest papers by meaning
- Learning To Solve Circuit-SAT: An Unsupervised Differentiable Approach (ICLR 2019 · similarity 0.91)
- NSNet: A General Neural Probabilistic Framework for Satisfiability Problems (NeurIPS 2022 · similarity 0.91)
- NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks (ICLR 2024 · similarity 0.88)
- Learning Better Representations From Less Data For Propositional Satisfiability (NeurIPS 2024 · similarity 0.87)
- Learning How to Cube (NeurIPS 2026 · similarity 0.87)
- HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.