arXiv:2610.27672v1 Announce Type: new Abstract: Rerunning every governance control after every change to an artificial intelligence (AI) pipeline is expensive, so teams reuse earlier results. Reuse i...
arXiv:2608. 09025v1 Announce Type: new Abstract: Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy.
arXiv:2607. 09712v1 Announce Type: new Abstract: Financial control testing increasingly depends on representative enterprise resource planning (ERP) data in quality environments, yet direct production copies expose personal, supplier, banking, and commercially sensitive records.
The paper introduces ClaimReceipt, a specification and verifier that checks whether a claim in an agent evaluation can be recomputed from retained evidence (sufficiency) and whether the evidence covers the entire experiment set (coverage). Using the CR‑2 verifier on 1,392 historical records, the authors demonstrate accurate reproduction of audit verdicts, non‑redundant field groups, and zero false positives on semantic faults. In a prospective CR‑3 run, the system correctly flags missing receipts and preserves coverage when private evidence is withheld, while adding minimal overhead to inference time and transaction size.
The paper introduces PACE (Policy‑Attested Contract Execution), a framework that sits between large‑language‑model (LLM) based autonomous AI agents and on‑chain DeFi operations. PACE defines typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind an approved intent, policy, and simulation report to the exact on‑chain execution bytes, providing replay and expiration protection. In evaluations across 40 tasks and six baselines, PACE achieves zero unsafe executions and zero false positives, outperforming unguarded agents by a large margin.
The paper introduces SecTB-RTL, an auditable framework for evaluating AI-generated RTL verification plans against 31 tasks and 124 hardware‑security regressions. In a confirmatory run, the AI model’s responses were rejected by the provider’s schema, and after a schema‑only repair, only nine of 1,857 accepted responses passed the production semantic validator, revealing a mismatch between generation and execution rules. The study demonstrates that schema acceptance does not guarantee execution validity and provides a benchmark, failure‑preserving contract, incident provenance, and governance controls to prevent misreporting of infrastructure behavior as model behavior.
The paper introduces NAQD‑Env, a synthetic benchmark designed to test language agents’ ability to selectively withdraw and resume actions when new evidence, permissions, or stop instructions arise. It evaluates models against a deterministic reference policy across eleven dependency families, measuring policy agreement, task value, withdrawal, resumption, and event reporting. Experiments on 350 scenarios show low withdrawal recall, no valid resumption, and limited policy alignment, highlighting the need to treat selective withdrawal as a distinct reliability component.
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
The paper introduces a source‑grounded integrity gate for AI‑assisted personal health records, ensuring that data generated by large language models remains provisional until a deterministic monitor verifies it against the source document. The monitor only accepts candidates that contain a unique supporting quotation, appear within the same laboratory row, and preserve provenance, preventing the model from approving its own output. In Medical DataCloud, the system passed all 22 conformance and mutation tests and, in a replay of nine historical lab reports, admitted 72 of 97 numeric candidates while retaining 25 for human review.
The paper shows that providing correctness feedback in the Verus/Rust verification workflow actually removes the evidence needed for completeness auditing, leading to a significant drop in certified witness yield compared to no‑feedback approaches. Experiments on 12 tasks across four model families demonstrate that independent discovery without feedback more than doubles the yield (59.0% vs. 27.1%) and that a phase‑separated execution can recover this yield without reusing responses. Preserving these witnesses also improves specification repair, with Phase‑Revised contracts achieving 81.3% implementation success versus 62.5% for IS‑Revised, while the effect does not appear in Dafny or Lean evaluations, indicating a specific limitation of the Verus/Rust workflow.
arXiv:2608. 02664v1 Announce Type: cross Abstract: Deploying ML models in regulated decision-making (credit underwriting, fraud detection, loan approval) requires demonstrating fairness and robustness to auditors without exposing model weights or customer data.
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside...