{"total":24,"rows":[{"id":"2505.23135","title":"VERINA: Benchmarking Verifiable Code Generation","created":"2025-05-29","cited_by_count":34,"area":null},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2510.25015","title":"VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","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":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2511.04355","title":"Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","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":"2510.12637","title":"COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions","created":"2025-10-14","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":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2603.25898","title":"On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2607.03174","title":"Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.08266","title":"On the Robustness of LLMs' Internal Representation of Code Correctness","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2608.21962","title":"NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2604.12311","title":"Is Vibe Coding the Future? An Empirical Assessment of LLM Generated Codes for Construction Safety","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.14113","title":"Simulating Students' Java Programming Errors with Large Language Models","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.06640","title":"Characterizing the Quality Profile of AI-Generated C++ in Production","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.14653","title":"Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.01601","title":"Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.14777","title":"LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}