Teacher Supervision, Fixed Representations and Calibration: Exact Risk Calculations for Candidate-Scoring Decision Models

Paper recorded by Signals 4 on 2026-10-19 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-19 on arXiv · recorded by Signals 4 on 2026-10-20

Category: cs.LG · 机器学习 · first seen 2026-10-20

Abstract

Candidate-scoring decision models return a probability distribution over a presented set of answers. Public documentation of one such system, Jev, and of an open counterpart, JevAny, describes three training ingredients that determine what these probabilities estimate: soft targets from larger models, a frozen pretrained backbone and temperature calibration. We analyze each ingredient in Gaussian

Read on arXiv →