# Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse

arXiv: https://arxiv.org/abs/2607.11967 · HTML: https://mlsanity.com/paper/2607.11967/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2110.06296/) (2021)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Neural collapse with unconstrained features](https://mlsanity.com/paper/2011.11619/) (2020)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [Understanding and Improving Transfer Learning of Deep Models via Neural Collapse](https://mlsanity.com/paper/2212.12206/) (2022)
- [Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold](https://mlsanity.com/paper/2604.00230/) (2026)

## Built on by (most cited first, 1 of 1)

- [Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells](https://mlsanity.com/paper/2609.11365/) (2026)

## Abstract (arXiv)

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.