SEP 4, 2026 · PREPRINT
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
arXiv
This is a machine learning systems paper demonstrating a novel framework for trade-up recommendation on a fixed benchmark and proxy catalog, but lacks validation on real-world deployment, clinical endpoints, or comparison to established baselines beyond a label-only variant.
Reported
AUC (reasoning-distilled student)0.924
95% CI for reasoning-distilled AUC[0.918, 0.929]
AUC (label-only student)0.912