Metraipolis › archive › dc_02f2cf9fa0ea

Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents — arXiv:2609.02127

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.02127
License (as archived): CC0-1.0
Archived: 2026-10-17T04:40:12.655Z
SHA-256 of the archived text: 0aa6be882ee0e6acb29ff850e7790107ebdc9483c198fa05bae28bd7d5eecdc8
Stable URL of this page: https://metraipolis.com/documento/dc_02f2cf9fa0ea

How to cite

Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents — arXiv:2609.02127 — arXiv (en), https://arxiv.org/abs/2609.02127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02f2cf9fa0ea (Metraipolis archive dc_02f2cf9fa0ea, sha256 0aa6be882ee0e6acb29ff850e7790107ebdc9483c198fa05bae28bd7d5eecdc8)

BibTeX

@misc{dc02f2cf9fa0ea,
  title = {Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents — arXiv:2609.02127},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02f2cf9fa0ea; sha256 0aa6be882ee0e6acb29ff850e7790107ebdc9483c198fa05bae28bd7d5eecdc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Persistent AI agents construct autobiographical state through reflection, retrieval, and consolidation. Persistence changes availability, not epistemic standing: stored or retrieved material is not thereby supported. Untrusted inputs, prompt injections, and model inferences can therefore enter persistent state and later be presented as agent history or user commitments. We specify typed provenance and assertion guardrails for autobiographical assertion boundedness, a system-relative release property requiring governed statements about the agent, user, or named relationships to satisfy accepted-evidence, temporal-validity, and disclosure policies. A typed provenance graph separates origin, dependency lineage, epistemic role, validity, and disclosure scope. A resolver evaluates authorized state projections and returns one evidential status, orthogonal conflict, staleness, and withholding flags, and a protected decision witness. A generate-verify-revise mediator then checks candidate semantic units before release and renders policy-authorized status responses. Under explicit assumptions about extraction, predicate correctness, resolution soundness, view declassification, and channel mediation, we prove a conditional assertion-boundedness contract. In an executable suite of 24 hand-authored conformance cases, typed mediation passed none of 19 unsafe opportunities unqualified while preserving all five supported controls. The flat/prior and source-tag comparison rules released 19/19 and 18/19 unsafe candidates, respectively. These results validate the encoded resolver and mediator obligations; they do not constitute an end-to-end evaluation of language models or retrieval systems.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.02127 — 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 2026-10-17T04:09:09.347Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).