Metraipolis › archive › dc_4dda326ae267

EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift — arXiv:2608.04278

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04278
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:39.410Z
SHA-256 of the archived text
b287864e613d134557127e1d3b4b97cedaa8f15356a9002e714021ff514caa07
Stable URL of this page
https://metraipolis.com/documento/dc_4dda326ae267

How to cite

EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift — arXiv:2608.04278 — arXiv (en), https://arxiv.org/abs/2608.04278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4dda326ae267 (Metraipolis archive dc_4dda326ae267, sha256 b287864e613d134557127e1d3b4b97cedaa8f15356a9002e714021ff514caa07)
BibTeX
@misc{dc4dda326ae267,
  title = {EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift — arXiv:2608.04278},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04278},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4dda326ae267; sha256 b287864e613d134557127e1d3b4b97cedaa8f15356a9002e714021ff514caa07},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 After an upstream change, a repository may still build even though earlier verification claims are no longer valid.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 known by construction. The task is to classify prior claims as unaffected, affected, or unprovable after value drift, logic drift, and deliberately withheld upstream content. The analysis covers 42 sessions across seven clean worlds, 14 model-world instances, three memory conditions, and two model tiers. In the Haiku round, artifact-anchored memory outscored prose notes and no persistent memory in all seven worlds; each exact paired Wilcoxon comparison yielded p = 0.0156. In the Sonnet round, the anchored condition was perfect, but frequent control ceilings left the preregistered contrasts non-significant. No session fabricated withheld content. These results support a bounded claim: artifact-anchored memory improved the smaller model's provability judgments in this testbed. An exploratory comparison further suggests that structured claim memory may narrow a capability gap by externalizing in-session re-derivation, but it does not establish cross- model equivalence. The study makes no claim about efficiency or repair quality.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04278 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T11:02:13.493Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).