Jeremy Avigad
Jeremy Avigad has 4 papers in our library, in 2023–2025, most of them on Reasoning; often with Joshua Clune, Sean Welleck, Albert Q. Jiang.
OpenAlex · ORCID · Wikidata · h-index 28 · 193 works · 3,227 citations OpenAlex, 2026-10-14
📄 4 works in our library · 🔗 Cited 141 times in our library · ⭐ Paper Stars ranking: #7289
Affiliations
🎓Carnegie Mellon UniversityPittsburgh ·
United States1996–2026 · 134 papersEmployment · Professor, Philosophy and Mathematical Sciences🎓Harvard UniversityCambridge ·
United StatesEducation🎓University of California, BerkeleyBerkeley ·
United StatesEducation
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksComputational Theory and Mathematics · 4 worksArts and Humanities · 1 workLanguage and Linguistics · 1 workMathematics · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work
Works by year
2020s
Papers
- ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics (2023 · 142 citations)
Autoformalization means converting informal mathematics into statements a proof assistant can check. Progress has been limited by the scarcity of paired informal and formal data. Existing prover benchmarks also lean on competition problems that require only a small set of elementary facts. To address this, the… - Duper: A Proof-Producing Superposition Theorem Prover for Dependent Type Theory (2024 · 8 citations)
Lean has no hammer, i.e. a tool that sends goals to external automatic provers and then rebuilds checkable proofs from their output. Building one for a dependently typed foundation is difficult. The authors present Duper, a superposition-based prover written in Lean that outputs proof terms directly in Lean's… - Premise Selection for a Lean Hammer (2025 · 5 citations)
Lean users often have to name, by hand, the exact lemmas that justify each small proof step, drawn from libraries with hundreds of thousands of facts. - ImProver: Agent-Based Automated Proof Optimization (2024 · 5 citations)
A Lean proof that compiles may still fall short: it can be verbose, hard to follow, or badly structured for library style rules or for use as machine-learning training data.
Co-authors here
- Joshua Clune ×2
- Sean Welleck ×2
- Albert Q. Jiang
- Bartosz Piotrowski
- Dragomir Radev
- Edward W. Ayers
- Hailey Schoelkopf
- Thomas Zhu
- Zhangir Azerbayev
Venues
- ITP 2024 (LIPIcs 309)
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jeremy-avigad/