Signals 4 · free daily AI digest

Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization

Paper recorded by Signals 4 on 2026-09-21 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.AI · 人工智能 · first seen 2026-09-22

Abstract

A model generalizes outside its training distribution only when it computes a representation structurally equivalent to the generating mechanism, not an approximation fitted to it. Such equivalence is necessary for exactness in and out of distribution, and extrapolation is governed by this exactness at inference, whatever its realization. Tensor Logic shows this: a zero-temperature contraction is

Read on arXiv →

#11 most recent of 340 cs.AI papers we have recorded · ↑ newer: Generative Tutorial: Towards Live Contextualized Visual Instructions f · ↓ older: Et Tu, Brute? Economic Misalignment in Personal AI Agents
Cite this page: Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization: the #11 most recent of 340 cs.AI papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/exactness-at-inference-a-representational-criterion-for-out-of-distribution-gene.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions