{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/clever-a-curated-benchmark-for-formally","title":"CLEVER: A Curated Benchmark for Formally Verified Code Generation","arxiv_id":"2505.13938","date":"2025-05-20","proceeding":null,"authors":["Amitayush Thakur","Jasper Lee","George Tsoukalas","Meghana Sistla","Matthew Zhao","Stefan Zetzsche","Greg Durrett","Yisong Yue","Swarat Chaudhuri"],"abstract":"We introduce ${\\rm C{\\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a held-out ground-truth specification, and (2) the task of generating a Lean implementation that provably satisfies this specification. Unlike prior benchmarks, ${\\rm C{\\small LEVER}}$ avoids test-case supervision, LLM-generated annotations, and specifications that leak implementation logic or allow vacuous solutions. All outputs are verified post-hoc using Lean's type checker to ensure machine-checkable correctness. We use ${\\rm C{\\small LEVER}}$ to evaluate several few-shot and agentic approaches based on state-of-the-art language models. These methods all struggle to achieve full verification, establishing it as a challenging frontier benchmark for program synthesis and formal reasoning. Our benchmark can be found on GitHub(https://github.com/trishullab/clever) as well as HuggingFace(https://huggingface.co/datasets/amitayusht/clever). All our evaluation code is also available online(https://github.com/trishullab/clever-prover).","url_abs":"https://arxiv.org/abs/2505.13938v3","url_pdf":"https://arxiv.org/pdf/2505.13938v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"clever-a-curated-benchmark-for-formally","repo_url":"https://github.com/trishullab/clever","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"clever-a-curated-benchmark-for-formally","repo_url":"https://github.com/trishullab/clever-prover","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"program-synthesis","task_name":"Program Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.13938","atlas_url":"https://app.syntology.ai/?focus=2505.13938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}