Sign inGet started
Paper · arXiv

EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift

Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it. After an upstream change, a repository may still build even though earlier verification claims are no longer valid. EA-Graph is an artifact-anchored memory for verification claims. It represents artifacts at sub-path granularity, resolves aliases to leaf definitions, anchors each claim to the content used to establish it, and keeps evidence strength separate from freshness. When replacement content is unavailable, the claim becomes unprovable rather than guessed. EA-Graph is evaluated on generated repositories whose behavior-to-artifact ground truth is kn...

AuthorsHwai-Jung Hsu, Cheng-Jan Chi, Hanna Everett
Primary categorycs.SE
Published4 August 2026
Last updated at source4 August 2026
cs.SEcs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/ca4a339b-42f9-4373-acb0-809eb421bd88" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.