Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Small Scale Reflection for the Working Lean User (2403.12733v1)

Published 19 Mar 2024 in cs.PL and cs.LO

Abstract: We present the design and implementation of the Small Scale Reflection proof methodology and tactic language (a.k.a. SSR) for the Lean 4 proof assistant. Like its Coq predecessor SSReflect, our Lean 4 implementation, dubbed LeanSSR, provides powerful rewriting principles and means for effective management of hypotheses in the proof context. Unlike SSReflect for Coq, LeanSSR does not require explicit switching between the logical and symbolic representation of a goal, allowing for even more concise proof scripts that seamlessly combine deduction steps with proofs by computation. In this paper, we first provide a gentle introduction to the principles of structuring mechanised proofs using LeanSSR. Next, we show how the native support for metaprogramming in Lean 4 makes it possible to develop LeanSSR entirely within the proof assistant, greatly improving the overall experience of both tactic implementers and proof engineers. Finally, we demonstrate the utility of LeanSSR by conducting two case studies: (a) porting a collection of Coq lemmas about sequences from the widely used Mathematical Components library and (b) reimplementing proofs in the finite set library of Lean's mathlib4. Both case studies show significant reduction in proof sizes.

Summary

We haven't generated a summary for this paper yet.