Metraipolis › archive › dc_852070ea6c97

When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority — arXiv:2609.20261

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20261
License (as archived)
CC0-1.0
Archived
2026-10-10T03:21:50.283Z
SHA-256 of the archived text
a15ba87dc71eee6ce5c62dff2aa874d9d24bf9e226c3a342988c59726759d972
Stable URL of this page
https://metraipolis.com/documento/dc_852070ea6c97

How to cite

When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority — arXiv:2609.20261 — arXiv (en), https://arxiv.org/abs/2609.20261 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_852070ea6c97 (Metraipolis archive dc_852070ea6c97, sha256 a15ba87dc71eee6ce5c62dff2aa874d9d24bf9e226c3a342988c59726759d972)
BibTeX
@misc{dc852070ea6c97,
  title = {When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority — arXiv:2609.20261},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20261},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_852070ea6c97; sha256 a15ba87dc71eee6ce5c62dff2aa874d9d24bf9e226c3a342988c59726759d972},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20261. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous agents derive concrete mutations from database reads, retrieved evidence, policy, beliefs, and delegated authority. Those inputs may change while reasoning is in progress. Database isolation orders the submitted transaction; agentic transaction processing determines whether a proposal satisfies an executable contract. Neither guarantee establishes a common valid point for the mutation and its derivation inputs unless the contract represents the relevant predicates. Typed dependency tokens distinguish content integrity from applicability, and trusted mediation captures the values exposed to reasoning. Under strict Cognitive Serializability, committed effects admit a serial order and a logical event at which every value exposed to derivation is unchanged. The fences last until the runtime event that realizes the sealed durability domain. The weaker Effect-Compatible Cognitive Admission recertifies an effect against a simultaneously held current dependency vector and current policy without claiming to serialize the original stochastic derivation. TCT combines immutable versioned executable definitions, registry-derived authority plans, sealed envelopes, guard-first commit transactions, post-seal envelope- and witness-bound grants, co-committed receipts, idempotent grant finalization, and receipt-driven epistemic reconciliation. Complete registered footprints and a single growing phase induce an acyclic lock-point order over local guards and incompatible external reservations. The corresponding results give serializability conditions and an observational-equivalence boundary for zero-error soundness and positive progress. A falsification suite tests the implementation obligations: the prototype prevented all injected anomalies and added 3.22 ms mean commit overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.20261 — 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 2026-10-10T03:04:13.723Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).