papers / checkout-consent

Checkout Consent: Measuring Authorization Before Agent Payments

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

abstract

Checkout consent binds a proposed purchase to a current total and shipping address. Checkout Consent evaluates this boundary in 40 synthetic shopping episodes across 7 scenario types. We test 9 scripted controls through the public execution and replay path. The privileged oracle attains full credit on 40/40 tasks, a rate of 1.000 [0.912, 1.000]. Empty output and blanket refusal receive no credit. Re-quoting after consent produces an unauthorized-attempt rate of 0.875 [0.739, 0.945]. These are 95% Wilson intervals over tasks. A simulated population sweep adds 16000 episodes and removes consent questions in a paired intervention. At equal oracle and unsafe-policy mixture weights, simulated mean score falls from 0.514 [0.491, 0.536] to 0.062 [0.055, 0.069]; intervals bootstrap simulated agents. The payment guard remains active throughout. Results validate selected measurement distinctions, not deployed agent safety. No learned model or human participant is evaluated.

benchmark: benchmark-checkout-consent. submitted to: none recorded.

citation

Arab, Pooria (2026). Checkout Consent: Measuring Authorization Before Agent Payments. https://doi.org/10.5281/zenodo.23752388

bibtex

@misc{checkout-consent,
  author = {Arab, Pooria},
  title = {Checkout Consent: Measuring Authorization Before Agent Payments},
  year = {2026},
  doi = {10.5281/zenodo.23752388},
  url = {https://pooriaarab.com/papers/checkout-consent},
}

venues, counts and the software records live on papers.