Introduces Knowledge-Based Pull Requests as a workflow that separates knowledge acceptance from code merge using agent distillation and project-side regeneration.
hub Mixed citations
Murphy-Hill, and Robert W
Mixed citation behavior. Most common role is background (60%).
17
Pith papers citing it
47
external citations · external index
Background
60% of classified citations
hub tools
citation-role summary
background 4
other 1
citation-polarity summary
representative citing papers
Participatory design study with 17 practitioners yields a three-level trust-calibrated review workflow for LLM-generated multi-file code changes, validated positively by 43 practitioners in survey.
CodeQL detected 171 CVEs total, with 83 caught by a prior version before the fix; detections were often actionable within the vulnerable file but not stable across tool versions.
CodeCureAgent achieves 96.8% plausible fixes and 86.3% correct fixes for 1,000 SonarQube warnings across 106 Java projects using an agentic LLM framework.
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
dille detects silent semantic faults in random forest ML pipelines with 91% precision via data-informed static analysis on Kaggle notebooks, finding 12-18% of scripts affected.
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
Case study of 18,020 Kubernetes PRs shows label-diff congruence is prevalent and stable, with higher congruence linked to fewer review participants among core developers and more among one-time contributors.
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.
XOXO is a cross-origin context poisoning attack on AI coding assistants that uses a Cayley Graph search algorithm (GCGS) to find stealthy perturbations, achieving 75.72% average success rate across five tasks and eleven models.
Analysis of 67,453 OpenClaw skills shows three scanners overlap on at most 10.4% of combined positives, with 81.9% flagged by only one scanner and distinct profiles for malicious versus suspicious skills.
A game-theoretic heterogeneous multi-agent architecture with three cloud LLMs and a local verifier achieves 77.2% F1, 100% recall, and 3x speedup for code vulnerability detection at $0.002 per sample on the NIST Juliet suite.
AI-native software ecosystems exhibit emergent behaviors best explained by complex adaptive systems theory, requiring new ecosystem-level monitoring and seven testable propositions that may extend or replace Lehman's laws.
Exploratory lab study finds shared LLM use builds shared understanding in design teams while parallel use risks context drift, with professionals reflecting on outputs for insights but sometimes anchoring early.
Developers anticipate code review staying central with more automation and broader scope, while highlighting tensions around understanding, accountability, and trust in AI-mediated processes.
DeepFWI is a multi-modal LSTM model with cross-attention that identifies bug-sensitive warnings at warning granularity, reaching 67.06% F1 on a 280k-warning dataset and surfacing 25 confirmed bugs in four open-source projects.
An empirical study of security DSLs and code analyzers finds few common concepts, overly general weakness descriptions, and that even experts are overwhelmed by the complexity of potential mappings.
citing papers explorer
-
Knowledge-Based Pull Requests: A Trusted Workflow for Agent-Mediated Knowledge Collaboration
Introduces Knowledge-Based Pull Requests as a workflow that separates knowledge acceptance from code merge using agent distillation and project-side regeneration.
-
Trust-Calibrated Code Review: A Participatory Design Study of Review Workflows for LLM-Generated Multi-File Changes
Participatory design study with 17 practitioners yields a three-level trust-calibrated review workflow for LLM-generated multi-file code changes, validated positively by 43 practitioners in survey.
-
Longitudinal Analyses of SAST Tools: A CodeQL Case Study
CodeQL detected 171 CVEs total, with 83 caught by a prior version before the fix; detections were often actionable within the vulnerable file but not stable across tool versions.
-
CodeCureAgent: Automatic Classification and Repair of Static Analysis Warnings
CodeCureAgent achieves 96.8% plausible fixes and 86.3% correct fixes for 1,000 SonarQube warnings across 106 Java projects using an agentic LLM framework.
-
NESA: Relational Neuro-Symbolic Static Program Analysis
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
-
Are We Lost in the Woods? Detecting Silent Semantic Faults for Random Forest Classifiers with Data-informed Static Analysis
dille detects silent semantic faults in random forest ML pipelines with 91% precision via data-informed static analysis on Kaggle notebooks, finding 12-18% of scripts affected.
-
PAFT: Preservation Aware Fine-Tuning for Minimal-Edit Program Repair
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
-
Efficiency for Experts, Visibility for Newcomers: A Case Study of Label-Code Alignment in Kubernetes
Case study of 18,020 Kubernetes PRs shows label-diff congruence is prevalent and stable, with higher congruence linked to fewer review participants among core developers and more among one-time contributors.
-
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.
-
XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
XOXO is a cross-origin context poisoning attack on AI coding assistants that uses a Cayley Graph search algorithm (GCGS) to find stealthy perturbations, achieving 75.72% average success rate across five tasks and eleven models.
-
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
Analysis of 67,453 OpenClaw skills shows three scanners overlap on at most 10.4% of combined positives, with 81.9% flagged by only one scanner and distinct profiles for malicious versus suspicious skills.
-
Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection
A game-theoretic heterogeneous multi-agent architecture with three cloud LLMs and a local verifier achieves 77.2% F1, 100% recall, and 3x speedup for code vulnerability detection at $0.002 per sample on the NIST Juliet suite.
-
More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
AI-native software ecosystems exhibit emergent behaviors best explained by complex adaptive systems theory, requiring new ecosystem-level monitoring and seven testable propositions that may extend or replace Lehman's laws.
-
The Role of LLMs in Collaborative Software Design
Exploratory lab study finds shared LLM use builds shared understanding in design teams while parallel use risks context drift, with professionals reflecting on outputs for insights but sometimes anchoring early.
-
Quo Vadis, Code Review? Exploring the Future of Code Review
Developers anticipate code review staying central with more automation and broader scope, while highlighting tensions around understanding, accountability, and trust in AI-mediated processes.
-
DeepFWI: Identifying Bug-Sensitive Warnings with Multi-Modal Code-Warning Semantics
DeepFWI is a multi-modal LSTM model with cross-attention that identifies bug-sensitive warnings at warning granularity, reaching 67.06% F1 on a 280k-warning dataset and surfacing 25 confirmed bugs in four open-source projects.
-
Can I Check What I Designed? Mapping Security Design DSLs to Code Analyzers
An empirical study of security DSLs and code analyzers finds few common concepts, overly general weakness descriptions, and that even experts are overwhelmed by the complexity of potential mappings.