papers / payment-delegation

Benchmark Payment Delegation: Policy Compliance and Useful Action in a Simulated Ledger

Pooria Arab · orcid 0009-0005-9964-6841 · 2026-10-29 · Published on Zenodo

abstract

Delegated payment agents must complete permitted work while respecting spending limits and owner authority. We present a synthetic ledger benchmark with 40 public episodes across 22 scenario templates. Native replay separates task success, ledger goal completion, and policy violations. Scripted reference success is 100.0% [91.2, 100.0] for the good policy and 0.0% [0.0, 8.8] for the bad policy. A constant OK response still scores 40.0% [26.3, 55.4], exposing weak evidence of informed refusal. Removing owner calls reduces success to 90.0% [76.9, 96.0]. A simulated population sweep varies selection between reference scripts and measures scoring sensitivity. All intervals are 95%; reference rates use Wilson intervals, and the simulated sweep resamples agent means. These results validate execution and expose scoring limits; they do not measure learned models, payment security in deployment, or human judgment.

benchmark: benchmark-payment-delegation. submitted to: none recorded.

citation

Arab, Pooria (2026). Benchmark Payment Delegation: Policy Compliance and Useful Action in a Simulated Ledger. https://doi.org/10.5281/zenodo.23752442

bibtex

@misc{payment-delegation,
  author = {Arab, Pooria},
  title = {Benchmark Payment Delegation: Policy Compliance and Useful Action in a Simulated Ledger},
  year = {2026},
  doi = {10.5281/zenodo.23752442},
  url = {https://pooriaarab.com/papers/payment-delegation},
}

venues, counts and the software records live on papers.