{"total":21,"rows":[{"id":"2505.23135","title":"VERINA: Benchmarking Verifiable Code Generation","created":"2025-05-29","cited_by_count":34,"area":null},{"id":"2509.22908","title":"A benchmark for vericoding: formally verified program synthesis","created":"2025-09-26","cited_by_count":20,"area":null},{"id":"2602.09464","title":"AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2603.19329","title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","created":"2026-03-18","cited_by_count":11,"area":null},{"id":"2602.18307","title":"VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean","created":"2026-02-20","cited_by_count":8,"area":null},{"id":"2510.06296","title":"VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2601.18944","title":"Neural Theorem Proving for Verification Conditions: A Real-World Benchmark","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2605.08553","title":"VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2509.23130","title":"SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2604.10392","title":"Intent-aligned Formal Specification Synthesis via Traceable Refinement","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2604.16584","title":"Certified Program Synthesis with a Multi-Modal Verifier","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2608.09277","title":"P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2608.13522","title":"Vero: Can AI Agents Build Formally Verified Software Repositories?","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2511.21104","title":"BRIDGE: Building Representations In Domain Guided Program Synthesis","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2603.14501","title":"CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.06184","title":"Teaching LLMs Program Semantics via Symbolic Execution Traces","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.22368","title":"VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.01008","title":"FVSpec: Real-World Property-Based Tests as Lean Challenges","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2609.39568","title":"Self-Spec Verifiable Code Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17358","title":"claimcheck: Measuring and Improving Specification Faithfulness","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}