Metraipolis › archive › dc_7bfa098312e4

HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems — arXiv:2608.22512

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22512
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:28.773Z
SHA-256 of the archived text: 61ce91d79ef880d732b6417c4897461e752a1c04f9c774b4c2e75b828b651fba
Stable URL of this page: https://metraipolis.com/documento/dc_7bfa098312e4

How to cite

HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems — arXiv:2608.22512 — arXiv (en), https://arxiv.org/abs/2608.22512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bfa098312e4 (Metraipolis archive dc_7bfa098312e4, sha256 61ce91d79ef880d732b6417c4897461e752a1c04f9c774b4c2e75b828b651fba)

BibTeX

@misc{dc7bfa098312e4,
  title = {HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems — arXiv:2608.22512},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22512},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bfa098312e4; sha256 61ce91d79ef880d732b6417c4897461e752a1c04f9c774b4c2e75b828b651fba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous multi-agent systems nowadays act in finance, software supply chains, and security operations. Already, the first largely AI-orchestrated intrusion campaigns have been reported. Yet, when such a system causes harm, no method can robustly establish what happened, what caused it, or who is accountable. This is because provenance forensics works at the wrong abstraction, formal causality assumes the causal model, and agent auditing trusts self-recording. The target failure mode is, thus, attribution laundering, i.e., spreading an act across redundant agents until none is a but-for cause. Worse, the record is produced by the suspects, which comprises the assumption adopted throughout this work. Agents may therefore anticipate the investigation and the part of logging infrastructure may itself collude. In this paper, HANSARD is proposed, a reference architecture treating accountability as a life-cycle property. First, a readiness profile sealed before operation bounds what later findings may claim. Second, capturing at five choke points beyond the agents' reach makes omissions detectable, not only tampering. Third, a typed PROV-DM-aligned causal graph accrues as the system runs, and three indicators read it live to gate oversight without adjudicating. Fourth, post-incident replay yields contingent effects under the modified Halpern-Pearl definition, together with a compensation-set size. Finally, a synergy residual measures harm due to the combination rather than to individuals, making laundering visible. Cause, responsibility and accountability are then reported separately, each capped by an evidentiary tier, while a future research agenda is also provided.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22512 — 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 2026-10-18T07:37:52.724Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).