Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Subfield
Neural and LLM-based formal theorem proving
Benchmarks: miniF2F, ProofNet, PutnamBench, LeanDojo Benchmark and others. Datasets: Mathlib proofs (LeanDojo extraction), Lean Workbook, Isabelle Archive of Formal Proofs, miniF2F statements. Baselines: GPT-f, HyperTree Proof Search, ReProver, Draft-Sketch-Prove and others.