AI 中文总结
该研究提出保留样本网络深度身份、分析表征轨迹的方法，发现计算路径可作为可靠信号，能提升OOD检测与图像分类性能，尤其对特定偏移效果显著。
AI 中文摘要
视觉模型不会一次性形成表征，每个模块都会对其进行修正。本文探究由此产生的计算路径是否包含最终表征所舍弃的证据，以及该证据能否提升分布外（OOD）检测和干净、偏移数据上的图像分类性能。与将中间层视为独立快照的方法不同，本文保留样本在网络深度上的身份，研究连接连续状态的变换，将类别一致的迁移与输入特有的创新区分开，还将坐标移动与关系重组区分开。在监督式、自监督式、视觉-语言、分层及卷积编码器中，这些路径展现出强样本特异性连续性和跨数据集重复出现的架构特异性深度分布，且具有实际应用价值：仅用分布内（ID）的过渡惊喜分数可补充强最终状态检测器，在平衡OpenOOD网格的152次非饱和比较中，将FPR95降低了131次；对于视觉破坏性和语义距离远的偏移，增益最大，且对多数检测器在近OOD上仍保持正增益；冻结更新探针在72个干净模型-数据集案例中提升了71个，而偏移数据的增益随架构和损坏类型变化。因此，计算路径提供了一种广泛有用的可靠性信号，其价值由模型组织和遇到的偏移共同决定。
英文摘要
Vision models do not form a representation at once; each block revises it. We ask whether the resulting computation path contains evidence that the final representation discards, and whether that evidence improves OOD detection and image classification on clean and shifted data. Unlike approaches that treat intermediate layers as separate snapshots, we retain sample identity across depth and study the transformations connecting successive states. We separate class-coherent transport from input-specific innovation, and coordinate movement from relational reorganization. Across supervised, self-supervised, vision--language, hierarchical, and convolutional encoders, these paths show strong sample-specific continuity and architecture-specific depth profiles that recur across datasets. They are also practically useful. An ID-only transition-surprise score complements strong final-state detectors, reducing FPR95 in 131/152 non-saturated comparisons on a balanced OpenOOD grid; gains are largest for visually disruptive and semantically far shifts, and remain positive on near-OOD for most detectors. Frozen update probes improve 71/72 clean model--dataset cases, while shifted-data gains vary with architecture and corruption type. Computation paths therefore provide a broadly useful reliability signal whose value is determined jointly by model organization and the shift encountered.
