Signals 4 · free daily AI digest

Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths

Paper recorded by Signals 4 on 2026-09-08 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-08 on arXiv · recorded by Signals 4 on 2026-09-09

Category: cs.LG · 机器学习 · first seen 2026-09-09

Abstract

Multi-step LLM reasoning lacks a machine-recheckable ledger: discarded reasoning paths leave no auditable record. We propose the Deposon scattering layer, which binds each node of an LLM-generated concept-decomposition graph to a two-parameter Deposon state; paths undergo three-channel scattering -- transmission, reflection, irreversible dissipation -- obeying T+R+A=1 for arbitrary parameters, wit

Read on arXiv →

#107 most recent of 215 cs.LG papers we have recorded · ↑ newer: Evaluation of Contextual Understanding in Large Language Models · ↓ older: Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm
Cite this page: Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths: the #107 most recent of 215 cs.LG papers we have recorded (as of 2026-09-08). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/deposon-an-auditable-conservation-guaranteed-game-theoretically-tested-scatterin.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG 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