# Auditing Frozen-Encoder Anomaly Detection Across Mechanical Systems: Representation Provenance, Calibration, and Protocol Effects

arXiv: https://arxiv.org/abs/2601.11415 · HTML: https://mlsanity.com/paper/2601.11415/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 6 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 1 of 1)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)

## Abstract (arXiv)

This version reports a reproducibility audit of the frozen-encoder experiments presented in version 1. The numerical discrimination results are reproducible from the preserved artifacts, but their original attribution to interferometric pretraining is not supported. The released checkpoint contains a nested model state that loads without missing parameters, whereas loading the outer checkpoint dictionary leaves almost the entire EfficientNet-B0 feature stack uninitialized. Preserved embeddings labelled as interferometric have norms of order 10-12, matching freshly initialized EfficientNet-B0 networks and differing by more than twelve orders of magnitude from the preserved ImageNet embeddings. A second, separately preserved near-zero embedding set produces almost the same IMS 4th-test anomaly scores (r=0.987) and record-level discrimination (AUC 0.9812 versus 0.9818). We therefore withdraw the causal claim that IMS performance demonstrates a morphological prior transferred from gravitational-wave instrumentation. We reanalyse the controlled IMS splits at matched observed false-positive rates and add multivariate classical signal baselines. The near-zero representations retain strong tail separation, particularly in the 2nd and 4th IMS runs, but this is now interpreted as an exploratory architecture-and-initialization effect coupled to Mahalanobis scoring. A separate PRONOSTIA audit shows that the original large warning times were induced by a lifetime-fraction baseline; under fixed-time evaluation, a ten-feature classical baseline outperforms the preserved encoder scores. These results illustrate how checkpoint provenance, finite-sample calibration, architecture, and target-domain baselines can create an appearance of cross-domain transfer. They also define the controls required before assigning physical meaning to frozen-representation anomaly scores.