AI & ML
Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing
arXiv cs.CR0 views
arXiv:2610.00327v2 Announce Type: replace Abstract: Tool-using agents can expose citations and execution logs while leaving a critical association unaudited: whether the claim shown to a user is the claim emitted by the committed execution and supported by the cited source. A valid citation and a valid trace can therefore remain individually well formed while being transplanted across claims, actions, runs, or source versions. We introduce a claim-anchored execution contract that jointly binds the emitted claim, its exact source span, the ordered execution prefix that produced it, and the source version and access state observed by that execution. Each receipt contains an emission anchor that deterministically locates the claim inside a committed answer or claim-bearing action, together with source identifiers, offsets, hashes, quotes, and a domain-separated execution commitment. A deterministic integrity verifier reconstructs these bindings before semantic or task labels are joined. We separate this integrity plane from a pluggable support plane, so structural validity is not used as a proxy for entailment. The contract exposes seven independently testable properties: claim-emission binding, source binding, ordered-execution binding, oracle separation, persisted-object replay, execution-rerun consistency, and version/access binding. Across 1,280 cross-object attacks, the joint contract detects 1,275 substitutions (0.9961). Removing a targeted property reduces its attack-detection rate to 0.0156-0.0625. On an independently adjudicated 384-pair split, the conflict-aware support guard reaches F1 0.8865 and false acceptance 0.0729; on unseen failure families, these rates are 0.8679 and 0.0938.
Source:https://arxiv.org/abs/2610.00327PreviousCapability-Gated Language Models: Security Composes, Utility Does NotNextCHAMP: Cayley HAshing with Matrix Products
Related posts

Copilot Fusion's Local Model Preview: Only One of Three Stages Runs on Your Machine
0dev.to AI

Meituan shipped LongCat-2.5
0dev.to AI
Standard bf16 Rounding Discards 99% of Your RL Policy Updates
0dev.to AI
Why Are Startups Choosing Coworking Space in Pune in 2026?
0dev.to AI
What a 32GB GPU actually lets you run locally
0dev.to AI

LLM weak random number generator detection test
0dev.to Security