Preprint
Jul 2026
From Neural Network Decisions to Training Cases: An Exact Account via Case-Based Decision Theory
This work shows that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition, and identifies a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence.
Manli Yan, Yu-Erh Lin, Yaowen Yu et al.
· 1 citation