{
  "schema_version": 2,
  "title": "Reproduction: Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving",
  "emoji": "🎯",
  "space_id": "SabaPivot/repro-beyond-theorem-proving-formulation-framework-and-benchmark-for-formal-problem-solving",
  "paper": {
    "arxiv_id": "2505.04528"
  },
  "tags": [
    "icml2026-repro",
    "paper-hgMZraPlSv"
  ],
  "updated_at": "2026-07-29T01:49:55+00:00",
  "root": {
    "slug": "index",
    "title": "Reproduction: Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving",
    "file": "pages/index.md",
    "children": [
      {
        "slug": "executive-summary",
        "title": "Executive summary",
        "file": "pages/executive-summary/page.md",
        "children": []
      },
      {
        "slug": "claim-1-formal-problem-solving-is-formulated-as-a-deterministic-markov-decision-process-and-implemented-inside-formal-theorem-proving-environments-section-3-1",
        "title": "Claim 1: Formal problem-solving is formulated as a deterministic Markov decision process and implemented inside formal theorem-proving environments (Section 3.1).",
        "file": "pages/claim-1-formal-problem-solving-is-formulated-as-a-deterministic-markov-decision-process-and-implemented-inside-formal-theorem-proving-environments-section-3-1/page.md",
        "children": []
      },
      {
        "slug": "claim-2-deductive-formal-problem-solving-decouples-forward-answer-construction-from-optional-backward-proof-validation-for-find-all-problems-figure-2",
        "title": "Claim 2: Deductive Formal Problem-Solving decouples forward answer construction from optional backward proof validation for find-all problems (Figure 2).",
        "file": "pages/claim-2-deductive-formal-problem-solving-decouples-forward-answer-construction-from-optional-backward-proof-validation-for-find-all-problems-figure-2/page.md",
        "children": []
      },
      {
        "slug": "claim-3-fps-soundness-holds-every-direct-answer-produced-by-fps-satisfies-the-formal-problem-predicate-theorem-3-6",
        "title": "Claim 3: FPS soundness holds: every direct answer produced by FPS satisfies the formal problem predicate (Theorem 3.6).",
        "file": "pages/claim-3-fps-soundness-holds-every-direct-answer-produced-by-fps-satisfies-the-formal-problem-predicate-theorem-3-6/page.md",
        "children": []
      },
      {
        "slug": "claim-4-d-fps-is-complete-and-sound-for-find-all-problems-under-the-paper-s-conditions-theorems-3-8-and-3-9",
        "title": "Claim 4: D-FPS is complete and sound for find-all problems under the paper's conditions (Theorems 3.8 and 3.9).",
        "file": "pages/claim-4-d-fps-is-complete-and-sound-for-find-all-problems-under-the-paper-s-conditions-theorems-3-8-and-3-9/page.md",
        "children": []
      },
      {
        "slug": "claim-5-the-benchmark-suite-consists-of-formalmath500-minif2f-solving-and-putnambench-solving-section-4-2",
        "title": "Claim 5: The benchmark suite consists of FormalMath500, MiniF2F-Solving, and PutnamBench-Solving (Section 4.2).",
        "file": "pages/claim-5-the-benchmark-suite-consists-of-formalmath500-minif2f-solving-and-putnambench-solving-section-4-2/page.md",
        "children": []
      },
      {
        "slug": "claim-6-the-strongest-reported-baselines-solve-at-most-23-77-27-47-and-0-31-of-the-three-benchmark-suites-respectively-table-1",
        "title": "Claim 6: The strongest reported baselines solve at most 23.77%, 27.47%, and 0.31% of the three benchmark suites respectively (Table 1).",
        "file": "pages/claim-6-the-strongest-reported-baselines-solve-at-most-23-77-27-47-and-0-31-of-the-three-benchmark-suites-respectively-table-1/page.md",
        "children": []
      },
      {
        "slug": "conclusion",
        "title": "Conclusion",
        "file": "pages/conclusion/page.md",
        "children": []
      }
    ]
  },
  "traces": [],
  "workspace": {
    "file": "workspace.json",
    "file_count": 0,
    "total_size": 0,
    "bucket_id": null
  },
  "agent_view_tokens": 5635,
  "trace_view_tokens": 10,
  "workspace_view_tokens": 8,
  "revision": "b8417f8df48bc6178891"
}