sparebrAIns: idle free-tier LLM compute pointed at machine-verified math. Lean 4 kernel is the judge.
-
Updated
Oct 23, 2026 - Lean
#
minif2f
Here are 5 public repositories matching this topic...
Faithfulness audit of the miniF2F Lean 4 port: 23 statements that do not say what their informal problems say, 13 with explicit counterexamples.
-
Updated
Sep 28, 2026
Faithfulness audit of miniF2F-v2 (v2s): 23 Lean 4 statements that do not say what their informal problems say, including 8 where the v2 correction introduced the defect.
-
Updated
Sep 28, 2026
Reproducibility audit of Goedel-Prover-V2-8B on miniF2F-test with the official pipeline: 201/244 (82.38%) vs the paper's 84.6%
-
Updated
Oct 15, 2026 - Shell
Open-source framework for formally verifying academic paper claims using multi-agent LLM debate + Z3/Knuckledragger proof certificates. Supports OpenAI, Anthropic, Google, Grok.
theorem-proving proof-assistant multi-agent debate z3 sympy smt-solver formal-verification ai-safety automated-reasoning scientific-research knuckledragger paper-review research-evaluation llm claim-verification minif2f
-
Updated
Jul 15, 2026 - Python
Add this topic to your repo
To associate your repository with the minif2f topic, visit your repo's landing page and select "manage topics."