Attributing Preprocessing Invariance in Spectral Foundation Models

On six Raman datasets the encoder does not measurably improve transfer over its normalization. It comes from a paper posted to arXiv on 18 September 2026. A spectral foundation model should remain useful when laboratories preprocess spectra differently. The standard test trains a classifier under one pipeline and evaluates under another, taking preserved accuracy as evidence of learned invariance. However, these models normalize each input before any learned parameter is applied. When normalization maps differently preprocessed spectra to the same vector, the encoder receives identical inputs and the measured invariance cannot be attributed to learning. We propose a normalization-only attribution control: compare the encoder against its normalization before interpreting transfer as learned invariance. A controlled experiment confirms invariance develops only when variation reaches the encoder past normalization. Across three systems, no encoder improves relative retention over its normalization. An audit of eighteen configurations across five modalities confirms the issue is widespread: the normalization-only control should be reported before crediting transfer to the encoder.

Why it counts

On six Raman datasets the encoder does not measurably improve transfer over its normalization. Across three systems, no encoder improves relative retention over its normalization.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.