The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models

Excerpt

arXiv:2610.08314v1 Announce Type: cross Abstract: Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each context label. However, whether this fixed-weight account describes pretrained tabular foundation models (TFMs) remains unclear. Testing this account using derivatives runs into a standardization trap: public TFM packages standardize the labels before the model sees them, yet ordinary derivatives