| [ | |
| "The paper formulates formal problem-solving as a deterministic Markov decision process and implements FPS inside formal theorem proving environments (Section 3.1).", | |
| "Deductive Formal Problem-Solving decouples forward answer construction from optional backward proof validation for find-all problems (Figure 2).", | |
| "FPS soundness is proved: any direct answer produced by FPS satisfies the formal problem predicate (Theorem 3.6).", | |
| "D-FPS completeness and soundness for find-all problems are stated as formal theorems under the paper's conditions (Theorems 3.8 and 3.9).", | |
| "The benchmark suite consists of FormalMath500, MiniF2F-Solving, and PutnamBench-Solving, constructed from informal and theorem-proving math benchmarks (Section 4.2).", | |
| "The strongest evaluated baselines solve at most 23.77% of FormalMath500, 27.47% of MiniF2F-Solving, and 0.31% of PutnamBench-Solving (Table 1)." | |
| ] | |