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 s...
Bo-Kang Zeng, Zhengguang Gao, Xiao-Yu Li et al.· 0 citations
This work introduces CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement that combines cross-space ranking robustness with low-cost architecture selection.
Yi-Fan Yang, Zhao-Yan Wang, Zhengguang Gao et al.· 1 citation
An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU model of Awasthi et al. (COLT 2024). For width $s$, at most $k$ active units per input, and effective weight and bias bo...
Xiao-Yu Li, Zhizhou Sha, Jiao-Jiao Jiang et al.· 0 citations
TRACE is presented, to the authors' knowledge the first agent watermark that is distortion-free in its action choices, self-synchronizing under deletion, and unconditionally invariant under rewriting, and it is proved this behavioral watermark's signal is bought with decision entropy.
We determine exactly what a kurtosis bound buys for one-sided tail control. For the class $\mathcal{C}(\kappa)$ of real random variables with mean $0$, variance $1$, and fourth moment at most $\kappa$, the skewness left free, we compute the worst-case tail probability $V_1(t,\kappa)=\sup_{X\in\mathcal{C}(\kappa)}\mathb...
Xiaoyu Li, Andi Han, Jiaojiao Jiang et al.· 0 citations
Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself. For a class of Natarajan dimension $d_N$ and Daniely-Shalev-Shwartz dimension $d_{DS}$, the optimal excess risk...
Xiao-Yu Li, Andi Han, Jiao-Jiao Jiang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
