SM
Sergey Mechtaev
cs.SEcs.AIcs.LGcs.PL
On Valency
published · living versionsW_a2m9q6nz·v1 · currentpublished
Validating Autoformalized Specifications via Contrapuntal Languages
with Yihan Dai, Xuanlin Liu, Haoxiang Jia, Tianchi Li +1
1 version
Preprints & journals
12 papers in the corpus · 2017–2026Validating Autoformalized Specifications via Contrapuntal Languages2610.30059v1 · Yihan Dai, Xuanlin Liu, Haoxiang Jia et al.2026 · 0 citationsarXivon Valency
Authority Is Not a String: A Capability-Scoped Harness for Prompt-Injection-Resistant Coding Agents2609.08371v1 · Dimitrios Stamatios Bouras, Yihan Dai, Sergey Mechtaev2026 · 0 citationsarXiv
Compressing Code Context for LLM-based Issue Resolution2603.28119v1 · Haoxiang Jia, Earl T. Barr, Sergey Mechtaev2026 · 1 citationarXiv
Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code2603.19239v2 · Dimitrios Stamatios Bouras, Sergey Mechtaev2026 · 0 citationsarXiv
Statistical Independence Aware Caching for LLM Workflows2511.22118v1 · Yihan Dai, Dimitrios Stamatios Bouras, Haoxiang Jia et al.2025 · 1 citationarXiv
Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation2511.12288v4 · Yihan Dai, Sijie Liang, Haotian Xu et al.2025 · 0 citationsarXiv
Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation2505.07270v3 · Haoxiang Jia, Robbie Morris, He Ye et al.2025 · 4 citationsarXiv
HoarePrompt: Structural Reasoning About Program Correctness in Natural Language2503.19599v3 · Dimitrios Stamatios Bouras, Yihan Dai, Tairan Wang et al.2025 · 0 citationsarXiv
The Fact Selection Problem in LLM-Based Program Repair2404.05520v3 · Nikhil Parasaram, Huijie Yan, Boyu Yang et al.2024 · 19 citationsarXiv
User-Centric Deployment of Automated Program Repair at Bloomberg2311.10516v1 · David Williams, James Callan, Serkan Kirbas et al.2023 · 9 citationsarXiv
Fairness-guided SMT-based Rectification of Decision Trees and Random Forests2011.11001v1 · Jiang Zhang, Ivan Beschastnikh, Sergey Mechtaev et al.2020 · 1 citationarXiv
Partitioning Patches into Test-equivalence Classes for Scaling Program Repair1707.03139v2 · Sergey Mechtaev, Xiang Gao, Shin Hwei Tan et al.2017 · 0 citationsarXiv
Career total: 44 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.