ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations
Quick summary
arXiv:2609.01992v1 Announce Type: new Abstract: Agent evaluations face two distinct evidentiary questions: whether a reported claim is recomputable from retained evidence (sufficiency), and whether the retained records cover the committed experiment set (coverage). Generic logs and hash-linked transcripts answer neither reliably. We introduce ClaimReceipt, a claim-relative receipt specification and selective verifier that binds typed transaction evidence to a signed experiment manifest and returns PASS, INVALID, or INCONCLUSIVE per claim. We freeze the specification before implementation (SHA-
Key takeaways
- arXiv:2609.01992v1 Announce Type: new Abstract: Agent evaluations face two distinct evidentiary questions: whether a reported claim is recomputable from retained evidence (sufficiency), and whether the retained records cover the committed experiment set (coverage).
- Generic logs and hash-linked transcripts answer neither reliably.
- We introduce ClaimReceipt, a claim-relative receipt specification and selective verifier that binds typed transaction evidence to a signed experiment manifest and returns PASS, INVALID, or INCONCLUSIVE per claim.
Why it matters
The importance of “ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments