POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.
arXiv preprint arXiv:2302.06527 , volume =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
VeriPort is an end-to-end agentic system that backports vulnerability patches to all affected versions of a package at scale while producing verification evidence, achieving 95.3% success on 128 benchmark tasks and generating over 5,000 verified patches across 169 CVEs.
Reviewer bots' higher comment volume on AI agent PRs is associated with slower resolutions and poorer average feedback quality, while feedback quality itself has no association with PR outcomes.
Co-locating tests with implementation code yields substantially higher preservation and correctness in foundation-model-generated programs than separated test syntax.
Ensemble Semantic Entropy improves correlation with code correctness over single-model methods and powers a cascading scaling system that cuts FLOPs by 64.9% while preserving performance on LiveCodeBench.
ClassInvGen co-generates class invariants and tests with LLMs to outperform pure LLM generation and Daikon on C++ data structures.
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
citing papers explorer
-
POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference
POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.
-
VeriPort: Automated and Verified Patch Backporting at Scale
VeriPort is an end-to-end agentic system that backports vulnerability patches to all affected versions of a package at scale while producing verification evidence, achieving 95.3% success on 128 benchmark tasks and generating over 5,000 verified patches across 169 CVEs.
-
On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories
Reviewer bots' higher comment volume on AI agent PRs is associated with slower resolutions and poorer average feedback quality, while feedback quality itself has no association with PR outcomes.
-
Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation
Co-locating tests with implementation code yields substantially higher preservation and correctness in foundation-model-generated programs than separated test syntax.
-
Ensemble-Based Uncertainty Estimation for Code Correctness Estimation
Ensemble Semantic Entropy improves correlation with code correctness over single-model methods and powers a cascading scaling system that cuts FLOPs by 64.9% while preserving performance on LiveCodeBench.
-
ClassInvGen: Class Invariant Synthesis using Large Language Models
ClassInvGen co-generates class invariants and tests with LLMs to outperform pure LLM generation and Daikon on C++ data structures.
-
Agentless: Demystifying LLM-based Software Engineering Agents
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.