Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach

• URL: http://arxiv.org/abs/2608.28542v1
• Date: Fri, 28 Aug 2026 17:18:49 GMT
• Title: Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach
• Abstract summary: Cross-organization agent require preserved evidence that remains independently verifiable during later audit or dispute review.<n>Existing mechanisms provide useful pieces, including authenticated logging, delegation semantics, signed checkpoints, and consistency checks.<n>We propose a preserved evidence-bundle model and a policy-controlled offline verifier for agent-to-agent workflow events.
• Score: 0.5801044612920815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-organization agent workflows require preserved evidence that remains independently verifiable during later audit or dispute review. They may involve multiple organizations, delegated actions, policy-relevant events, and disputed accountability claims. This is difficult when live systems are unavailable, controlled by one party, or not trusted by all participants. Existing mechanisms provide useful pieces, including authenticated logging, delegation semantics, signed checkpoints, and consistency checks. What remains missing is a verifier-centered event-level bundle for checking evidence sufficiency offline under an explicit policy. We propose a preserved evidence-bundle model and a policy-controlled offline verifier for agent-to-agent workflow events. Each bundle preserves policy-required evidence, including sender authentication, authenticated log commitment, witness-backed checkpoint evidence, append-only continuity, delegation-aware authorization evidence, and explicit receiver-signed receipt evidence when required. The verifier accepts only claims supported by the selected policy-required evidence, giving a later reviewer an offline basis for assessing evidence sufficiency. It does not infer delivery or receipt from transport behavior or log inclusion alone. In a prototype evaluation over 300 complete workflows and 1200 valid preserved bundles, we measure offline verifier-side latency across policy profiles and workflow-event evidence requirements. Checkpoint-context anchoring has the highest latency in the current prototype, while delegation and workflow-prerequisite evidence require additional verification steps. In targeted negative-evidence tests, all corrupted or policy-insufficient bundles were rejected, with no false acceptance observed. These results support evidence-based audit and dispute review without relying on live services or platform-specific logs.

Related papers

• An Evidence Model for Agentic Processes: Evidence Claims, Trust Assumptions, and Policy Assessment [0.0]
  This paper proposes an evidence claim model for agentic processes.<n>It distinguishes artifact integrity, temporal existence, provenance, approval evidence, declared ordering, capture claim, relevance claim, deliberation traceability, monitoring claim, anchoring authorization claim, policy assessment claim, risk treatment claim, mitigation implementation claim, and management response claim.<n>The model maps these claims to mechanisms, assumptions, limitations, and threats, and situates them in an agent organization with functional CEO agent, executive, operational, evidence, and audit roles, plus a plan-do-check-act-inspired management response loop.
  arXiv  Detail & Related papers  (2026-09-08T09:25:28Z)
• The Verification Gap in Networked Physical AI: A Post-Semantic Communication Framework [0.7896651877485362]
  In networked Physical AI, a proposal may be understood while valid, timely, proposal-bound evidence or the authority required to finalize an action remains unavailable.<n>We call this mismatch the verification gap and introduce a Post-Semantic Communication Framework for the systems interface between proposal formation and physical execution.
  arXiv  Detail & Related papers  (2026-08-20T03:17:20Z)
• From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents [47.678562263387214]
  Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings.<n>Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings.<n>We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification.
  arXiv  Detail & Related papers  (2026-08-05T13:37:38Z)
• The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering [67.8271652641864]
  We study whether verifier strictness can be controlled through hidden-state intervention.<n>VerifySteer exploits latent correctness signals for sample-level routing and selectively intervenes on paragraph boundaries.
  arXiv  Detail & Related papers  (2026-05-20T05:48:16Z)
• Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision [1.7044563989708406]
  We introduce case-grounded evidence verification.<n>We train a standard verifier on the resulting support task.<n>Results suggest that a major bottleneck in evidence grounding is not only model capacity, but the lack of supervision.
  arXiv  Detail & Related papers  (2026-04-10T17:55:38Z)
• Verification of Robust Properties for Access Control Policies [51.736723807086385]
  Existing methods for verifying access control policies require the policy to be complete and fully determined before verification can proceed.<n>We introduce robust property verification: the problem of determining what a policy's structure commits it to regardless of how pending decisions are resolved and regardless of subsequent extension.<n>We show that despite quantifying universally over all possible policy extensions the judgment reduces to proof search in a second-order logic programming language.
  arXiv  Detail & Related papers  (2026-03-13T17:14:38Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• zkToken: Empowering Holders to Limit Revocation Checks for Verifiable Credentials [0.0]
  We propose a novel framework for time-limited continuous verification.<n>The system guarantees proven untraceability of the revocation status after the verification period expires.<n>In addition to theoretically proving security, we evaluate the approach analytically and experimentally.
  arXiv  Detail & Related papers  (2025-09-15T13:48:41Z)
• Evidence Tampering and Chain of Custody in Layered Attestations [0.0]
  In distributed systems, trust decisions are made on the basis of integrity evidence generated via remote attestation. We present algorithms for identifying all such tampering opportunities for given evidence as well as tampering "strategies" by which an adversary can modify incriminating evidence without being detected. Our efforts are intended to help protocol designers ensure their protocols reduce evidence tampering opportunities to the smallest, most trustworthy set of components possible.
  arXiv  Detail & Related papers  (2024-01-31T21:54:53Z)
• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification [118.03466985807331]
  We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.<n>We introduce the feedback-based evidence retriever(FER) that optimize the evidence retrieval process by incorporating feedback from the claim verifier.
  arXiv  Detail & Related papers  (2023-10-18T02:59:38Z)
• Complex Claim Verification with Evidence Retrieved in the Wild [73.19998942259073]
  We present the first fully automated pipeline to check real-world claims by retrieving raw evidence from the web. Our pipeline includes five components: claim decomposition, raw document retrieval, fine-grained evidence retrieval, claim-focused summarization, and veracity judgment.
  arXiv  Detail & Related papers  (2023-05-19T17:49:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.