Pith. sign in

REVIEW 11 cited by

LeanExplore: A search engine for Lean 4 declarations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.11085 v1 pith:FPBJJVLB submitted 2025-06-04 cs.SE cs.AIcs.CLcs.IRcs.LGcs.LO

LeanExplore: A search engine for Lean 4 declarations

classification cs.SE cs.AIcs.CLcs.IRcs.LGcs.LO
keywords leanleanexploresearchenginedeclarationsusersdeclarationhttps
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The expanding Lean 4 ecosystem poses challenges for navigating its vast libraries. This paper introduces LeanExplore, a search engine for Lean 4 declarations. LeanExplore enables users to semantically search for statements, both formally and informally, across select Lean 4 packages (including Batteries, Init, Lean, Mathlib, PhysLean, and Std). This search capability is powered by a hybrid ranking strategy, integrating scores from a multi-source semantic embedding model (capturing conceptual meaning from formal Lean code, docstrings, AI-generated informal translations, and declaration titles), BM25+ for keyword-based lexical relevance, and a PageRank-based score reflecting declaration importance and interconnectedness. The search engine is accessible via a dedicated website (https://www.leanexplore.com/) and a Python API (https://github.com/justincasher/lean-explore). Furthermore, the database can be downloaded, allowing users to self-host the service. LeanExplore integrates easily with LLMs via the model context protocol (MCP), enabling users to chat with an AI assistant about Lean declarations or utilize the search engine for building theorem-proving agents. This work details LeanExplore's architecture, data processing, functionalities, and its potential to enhance Lean 4 workflows and AI-driven mathematical research

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MechMath Agent Team: LLM Driven Agents for Mathematical Research

    cs.AI 2026-07 conditional novelty 7.0 partial

    A decoupled multi-agent LLM system (Harness + KB/NL/FL provers) co-piloted solutions to 11 open math problems, some with Lean formalization.

  2. LAMP: Lean-based Agentic framework with MCP and Proof Repair

    cs.LO 2026-06 conditional novelty 7.0

    LAMP achieves 96.7% success generating verified Lean proofs for 90 Combinatorics on Words theorems by coordinating Planner, Builder, and Verifier agents with a CoW ontology accessed through Model Context Protocol.

  3. Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models

    cs.CL 2026-06 unverdicted novelty 7.0

    Current embedding models fail to capture mathematical equivalence across lexical variants, but contrastive alignment of informal and formal statements improves retrieval on both equivalence and formalization tasks.

  4. LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving

    cs.IR 2026-05 conditional novelty 7.0

    LeanSearch v2 recovers 46.1% of ground-truth premise groups on research-level Mathlib theorems and raises fixed-loop proof success from 4% to 20% via embedding-reranker plus iterative sketch-retrieve-reflect retrieval.

  5. LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving

    cs.IR 2026-05 conditional novelty 7.0

    LeanSearch v2 recovers 46.1% of ground-truth premise groups for research-level Lean 4 theorems within 10 candidates and raises fixed-loop proof success to 20%.

  6. Matlas: A Semantic Search Engine for Mathematics

    cs.IR 2026-04 unverdicted novelty 7.0

    Matlas introduces a semantic retrieval system over 8.07 million mathematical statements from papers and textbooks, using dependency graphs and topological unfolding for self-contained search via natural language queries.

  7. Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models

    cs.CL 2026-06 unverdicted novelty 6.0

    Embedding models fail to capture mathematical equivalence due to lexical bias, but contrastive training on informal-formal pairs improves performance on MELD and retrieval tasks.

  8. OpenProver: Agentic and Interactive Theorem Proving with Lean 4

    cs.AI 2026-07 conditional novelty 5.0

    OpenProver is an open-source Planner-Worker-Verifier ATP system with Lean 4 that raises ProofNet success rates over linear LLM rollouts and adds interactive human guidance.

  9. Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

    cs.CL 2026-05 unverdicted novelty 5.0

    MathArena is broadened into a maintained platform with new benchmarks for proofs, research questions, and formal verification, where GPT-5.5 scores 98% on 2026 USAMO and 74% on research-level tasks.

  10. Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

    cs.CL 2026-05 unverdicted novelty 5.0

    MathArena is a maintained platform evaluating LLMs across olympiad problems, proofs, research questions, and formal proofs, with GPT-5.5 reaching 98% on 2026 USAMO and 74% on research-level tasks.

  11. AI for Mathematics: Progress, Challenges, and Prospects

    math.HO 2026-01 unverdicted novelty 4.0

    AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.