paperSeptember 2026Unreviewed

TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

Abstract

Watermarking the final patch produced by a coding agent provides provenance evidence for the submitted artifact, but does not authenticate the visible process that produced it. Behavioral watermarking methods primarily provide a global detection or identifier-recovery signal, so a locally edited trajectory may retain sufficient ownership evidence without revealing which protected region has become inconsistent. To address this limitation, we propose TrajMark, a training-free, symmetric-key, visi

Cite

@misc{zeng2026trajmark,
  title = {{TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories}},
  author = {Bokang Zeng and Zheng Gao and Xiaoyu Li and Xiaoyan Feng and Jiaojiao Jiang},
  year = {2026},
  month = sep,
  eprint = {2609.10416},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.10416}
}