发现神经网络收敛后仍可识别独特功能指纹，验证了跨模型比较的可行性。
Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse
- 通过仿射校正对齐不同网络，消除坐标自由度干扰
- 20组配对中全部正确识别，置换检验p值0.0083
- 适用于研究网络间功能差异的可控实验场景
独立训练的神经网络因无共享神经元索引参考系，比较时需考虑坐标自由度。神经坍缩使网络收敛至共享低维几何结构，引发疑问：收敛后轨迹特异性功能差异是否仍可区分？本文区分可检测性、可移植性和因果持续性三类假设，聚焦可检测性。在MNIST上使用五个独立训练的实现神经坍缩的网络，采用经验证的仿射校正映射将源网络头转换到目标网络坐标系。在目标基线校正后，源网络的功能指纹仍可区分：全部20组有序源-目标配对均被正确识别，置换检验p=0.0083，且对泄漏审计具有鲁棒性。结果证明在本测试条件下可检测性成立，但无法确认可移植性或因果持续性。研究展示了对齐、歧义诊断与泄漏控制如何协同验证跨网络功能变异，其是否可推广至更广场景尚待探索。
原文摘要 · Abstract (English)
Independently trained neural networks have no shared neuron-index reference frame, so comparing them requires accounting for coordinate freedom. Neural Collapse sharpens this problem: networks converge toward a shared, low-dimensional geometry, raising the question of whether trajectory-specific functional variation remains distinguishable after convergence. We distinguish three claims - detectability, transplantability, and causal persistence - and address the first. Using five independently trained networks reconstructing Neural Collapse on MNIST, we apply a verified affine-correct alignment mapping donor heads into recipient coordinates. Donor-specific functional fingerprints remain distinguishable after recipient-level baseline correction: all 20 ordered donor-recipient pairs are correctly identified, with an exact permutation p=0.0083, robust to a leakage audit. These findings establish detectability under the test used here, but not transplantability or causal persistence. The study shows how alignment, ambiguity diagnostics, and leakage control combine to test cross-network variation in a controlled setting; whether this generalizes beyond it is open.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。