aiqbench analysis
This paper introduces the Combined Evidence Protocol (CEP), a mechanism allowing autonomous AI agents to verify that boundary-setting entities adhere to their own published rules without relying on centralized trust or new intermediaries. By leveraging recomputation from anchored data, similar to optimistic rollups, it enables mutually distrusting peers in an open agent ecosystem to independently validate rule application and dissolve the oracle problem inherent in decentralized governance.
Trust Without Trusting: A Recomputable Trust Protocol for Autonomous Agents
arXiv:2605.06738v2 Announce Type: replace-cross Abstract: Autonomous AI agents already transact at production scale -- 69,000 bots, 165 million transactions, $50 million in volume on a single marketplace -- and any party can verify a signed credential without a central service. In an open agent world that covers most of what trust requires: there are no universal borders, and each party chooses for itself whom to deal with. Borders appear only where a closed space draws one -- a marketplace, a platform, or a consortium sets house rules. Whoever draws the border holds the authority to apply it, and may apply it as they choose, behind closed doors. This paper addresses the gap that opens there: when you rely on someone else's border, how do you check that they applied their own published rules -- taking no one's word for it, and handing the check to no new trusted party? Our answer is the Combined Evidence Protocol (CEP): a five-condition predicate any party recomputes from anchored data, turning "did the boundary-owner follow its own admission rules" into a fact anyone verifies rather than a claim anyone believes. The move that secures optimistic rollups secures this -- correctness rests on recomputation, so the measurement belongs to everyone and the oracle problem dissolves. Its load-bearing setting is a consortium of co-equal, mutually distrusting peers under a shared charter, each able to verify, independently, that the rules they jointly agreed are the rules being applied. CEP belongs to the family of trustless systems -- optimistic and zero-knowledge rollups, verifiable ML, self-sovereign-identity predicates. The infrastructure beneath it is live: a W3C VC + DID trust layer running since March 2026, anchored on Base L2, continuing arXiv:2605.06738 and standing on its own.
Abstract:Autonomous AI agents already transact at production scale -- 69,000 bots, 165 million transactions, $50 million in volume on a single marketplace -- and any party can verify a signed credential without a central service. In an open agent world that covers most of what trust requires: there are no universal borders, and each party chooses for itself whom to deal with. Borders appear only where a closed space draws one -- a marketplace, a platform, or a consortium sets house rules. Whoever draws the border holds the authority to apply it, and may apply it as they choose, behind closed doors. This paper addresses the gap that opens there: when you rely on someone else's border, how do you check that they applied their own published rules -- taking no one's word for it, and handing the check to no new trusted party? Our answer is the Combined Evidence Protocol (CEP): a five-condition predicate any party recomputes from anchored data, turning "did the boundary-owner follow its own admission rules" into a fact anyone verifies rather than a claim anyone believes. The move that secures optimistic rollups secures this -- correctness rests on recomputation, so the measurement belongs to everyone and the oracle problem dissolves. Its load-bearing setting is a consortium of co-equal, mutually distrusting peers under a shared charter, each able to verify, independently, that the rules they jointly agreed are the rules being applied. CEP belongs to the family of trustless systems -- optimistic and zero-knowledge rollups, verifiable ML, self-sovereign-identity predicates. The infrastructure beneath it is live: a W3C VC + DID trust layer running since March 2026, anchored on Base L2, continuing arXiv:2605.06738 and standing on its own.
18 pages, 5 figures. v2: substantial revision, reframed around recomputable accountability (Combined Evidence Protocol); adds figures, code listings, and deployment evidence. Supersedes v1 (From Specification to Deployment)
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2605.06738 [cs.CR]
(or arXiv:2605.06738v2 [cs.CR] for this version)
Full text under the publisher's open licence · 323 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

Agent identity architectures: Delegated, bounded, and autonomous
1Password · Jun 26, 2026

Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · Oct 5, 2026

Delegated authority, running locally: Give an agent on your machine an identity you can trust
1Password · Jul 21, 2026