DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
hub Canonical reference
In: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering
Canonical reference. 80% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
ConCovUp uses static analysis to ground LLM test generation and backward tracing to produce concurrent test drivers that raise average shared-memory access pair coverage from 36.6% to 68.1% on nine real-world libraries.
An encoding of Solidity contracts and first-order Hennessy-Milner logic into Lustre enables Kind 2 model checking of complex temporal properties in smart contracts.
A survey of 419 practitioners shows strong reliance on reusable GitHub Actions for core CI/CD tasks but limited adoption of reusable workflows, with copy-pasting remaining common due to versioning and trust issues.
Empirical analysis of 338 PRs with self-admitted ChatGPT usage shows low full integration (median 25%), selective adaptation patterns, and broader influence on developer reasoning during reviews.
MR-Adopt deduces input transformations from hard-coded MR test cases using LLMs, data-flow refinement, and output-relation selection to enable reuse with new source inputs.
FAUDITOR is a specialized fuzzer that detected 220 zero-day monetarily exploitable vulnerabilities in smart contracts by combining finance-interface targeting, NLP from auditor reports, and self-learning.
Augmenting LLMs with bug references, few-shot learning, chain-of-thought, and RAG improves MPI error detection accuracy from 44% to 77% and generalizes across models.
Specificity and Context predict actionable code generation while Verification predicts adoption and Context predicts integration depth in LLM-assisted PR workflows.
LogCopilot is an LLM framework that builds a hierarchical knowledge base from logs and generates/executes LogQL queries from natural language instructions, reporting 76.8% average accuracy across four datasets.
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
citing papers explorer
-
Code Generation by Differential Test Time Scaling
DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
-
ConCovUp: Effective Agent-Based Test Driver Generation for Concurrency Testing
ConCovUp uses static analysis to ground LLM test generation and backward tracing to produce concurrent test drivers that raise average shared-memory access pair coverage from 36.6% to 68.1% on nine real-world libraries.
-
KindHML: formal verification of smart contracts based on Hennessy-Milner logic
An encoding of Solidity contracts and first-order Hennessy-Milner logic into Lustre enables Kind 2 model checking of complex temporal properties in smart contracts.
-
Automation and Reuse Practices in GitHub Actions Workflows: A Practitioner's Perspective
A survey of 419 practitioners shows strong reliance on reusable GitHub Actions for core CI/CD tasks but limited adoption of reusable workflows, with copy-pasting remaining common due to versioning and trust issues.
-
PatchTrack: A Comprehensive Analysis of ChatGPT's Influence on Pull Request Outcomes
Empirical analysis of 338 PRs with self-admitted ChatGPT usage shows low full integration (median 25%), selective adaptation patterns, and broader influence on developer reasoning during reviews.
-
MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing
MR-Adopt deduces input transformations from hard-coded MR test cases using LLMs, data-flow refinement, and output-relation selection to enable reuse with new source inputs.
-
Capturing Monetarily Exploitable Vulnerability in Smart Contracts via Auditor Knowledge-Learning Fuzzing
FAUDITOR is a specialized fuzzer that detected 220 zero-day monetarily exploitable vulnerabilities in smart contracts by combining finance-interface targeting, NLP from auditor reports, and self-learning.
-
Improving MPI Error Detection and Repair with Large Language Models and Bug References
Augmenting LLMs with bug references, few-shot learning, chain-of-thought, and RAG improves MPI error detection accuracy from 44% to 77% and generalizes across models.
-
Prompt Quality and Pull Request Outcomes: A Stage-Based Empirical Study of LLM-Assisted Development
Specificity and Context predict actionable code generation while Verification predicts adoption and Context predicts integration depth in LLM-assisted PR workflows.
-
LogCopilot: Automating Log Aggregation Analysis through Large Language Models
LogCopilot is an LLM framework that builds a hierarchical knowledge base from logs and generates/executes LogQL queries from natural language instructions, reporting 76.8% average accuracy across four datasets.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.