Research map / Large language models / Agents, code and math
Learning Reliable Logical Rules with SATNet
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 |
|---|---|---|---|
| inject partial domain knowledge into the C matrix | SATNet* · real-world applications | performance | Helped |
| sparsify the C matrix | SATNet* · learned logical rules | expressive power and solving time | Mixed |
| use an exact solver instead of coordinate descent | SATNet* · assignment solving | solution reliability | Helped |
Closest papers by meaning
- SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver (ICML 2019 · similarity 0.94)
- Learning Symmetric Rules with SATNet (NeurIPS 2022 · similarity 0.90)
- Assessing SATNet's Ability to Solve the Symbol Grounding Problem (NeurIPS 2020 · similarity 0.89)
- NSNet: A General Neural Probabilistic Framework for Satisfiability Problems (NeurIPS 2022 · similarity 0.89)
- Learning Better Representations From Less Data For Propositional Satisfiability (NeurIPS 2024 · similarity 0.88)
- Can Transformers Reason Logically? A Study in SAT Solving (ICML 2025 · 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.