ResearchCode Fingerprints Model-Specific Attribution of LLM-Generated CodearXiv·high signalXBlueskyLinkedInCopy linkBeyond binary human-vs-machine: identifies which specific LLM generated a code snippet. For distillation detection and compliance.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerHierarchical Ransomware Agents Escalate to Dynamic and Memory Analysis Only on Specialist DisagreementarXiv 2609.04820Stack layer / Threat pattern16% of 3,171 public agent-harness setups carry a confirmed security defect, and 3.8% ship a skill that pre-approves your shellarXivPolicy dependency / Stack layerAgents hit 80% F1 deciding whether a dependency CVE is exploitable, but fall below 70% explaining whyarXiv 2609.08040Policy dependency / Stack layer83.3% of 281 open-source AI contribution policies permit AI code, but 67.3% demand a high level of human involvementarXivStack layer / Contrast67% of Material Changes to Frontier AI Safety Frameworks Are Made Without the Developer Saying SoarXiv 2609.08789Stack layer / Update threadThe Agentic SDLC Throughput Paradox: Coding Gains Attenuate Sharply Between Writing Code and Shipping ItarXiv 2609.04681Stack layer / Threat patternIntentest externalizes long-horizon pentest state onto a fact-intent DAG to stop agents loopingarXivPolicy dependency / Stack layerEnriching the Environment's Feedback Beats Warming Up the Agent for Sparse Long-Horizon RLarXiv 2609.08404