Resolve decoder-logit probe differences among spectral representations
Determine whether continuous spectra, hard category codes, and category-posterior inputs produce different balanced accuracies for decoder-logit probes after frozen decoding.
References
Decoder-logit probe differences remain unresolved.
— SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces
(2610.19651 - Hsu, 14 Oct 2026) in Section 5, subsection “Calibrating Recognition and Disturbance”