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 layerAn audit of a production agent pipeline found a reported p99 latency of 2,147,483,647 ms, the signed 32-bit maximum, from a lifecycle clamparXiv 2609.12017Policy dependency / Stack layerMOSAIC Picks a GraphRAG Traversal Policy per Query and Beats the Best Fixed Policy by 9.96 PointsarXiv 2609.11065Stack layer / Threat pattern787,562 Function Pairs Show AI Code Is Half the Size of Human Code With Different Defect Classes, Not FewerarXiv 2609.12708Policy dependency / Stack layerCodeBLEU Scored 91% for Both RAG Strategies While One of Them Hallucinated APIs 56.4% of the TimearXiv 2609.12464Stack layer / ContrastDistilled Byte Models Match a Token Model's Accuracy on One-Sixth the Data and Cut Logit Storage to a FiftharXiv 2609.12303Stack layer / Update threadSplitting a CTF Task Into Isolated Sub-Contexts Lets a Local gemma-4 Solve 18.52% of Challenges Standard Agent Loops FailarXiv 2609.12839Stack layer / Update threadAIM Adds Index-Level Access Control to Agent Memory and Ships MUMBench for Multi-User Memory OperationsarXiv 2609.12320Policy dependency / Stack layerRIPPLE: an edit confined to one prompt-policy segment changes downstream behavior, so replay candidate edits after previously accepted ones before persistingarXiv 2609.12127