Sources

Essential reading

• Verification for International AI Governance

  B. Harack et al. (2025) · Technical report · Oxford Martin AI Governance Initiative

  Appendix L.4 describes the timed model-residency proposal. Footnote 437 sets the desired timing, memory dependence and low overhead, and suggests challenges over random portions of weights if a whole-model challenge is too costly.

  Bibliography [1]

Complete bibliography

1. Tier B. B. Harack et al. (2025). Verification for International AI Governance. Oxford Martin AI Governance Initiative. Source recordSupports: loaded-model goal; timed software variant; model-loading assumption; unpredictable challenges; neutral batch checking; simultaneous inventory challenges; whole-model or shard requirement; random-weight variant; roughly 50 ms target; construction and attack testing left open · Appendix L.4, pp. 159–160, especially footnote 437
2. Tier B. S. K. Monfared et al. (2026). Timing and Memory Telemetry on GPUs for AI Governance. arXiv. Source recordSupports: the separate VRAM-residency experiment challenges verifier-supplied data · §3; §4.3