01 / The mechanism and its boundary
What is being described
A positive claim asserts that something is present or happened, and a negative claim asserts that an activity or resource is absent S-0004; a mixed claim bundles both.
Examples are the declared model being the one served (positive), there being no undeclared compute (negative) and compute running inference and not training (mixed). The Oxford Martin report observes that demonstrating the existence of an object or process is often straightforward compared with demonstrating its non-existence S-0004. RAND's framework mirrors the split: one subgoal verifies that declared uses of compute are accurate, and another verifies that there are no undeclared uses and no undeclared clusters S-0002. Proposed designs support negative claims indirectly:
- Leaving no spare capacity. Filling or wiping memory removes residual capacity for hidden workloads, as in memory wiping and proofs of secure erasure S-0018.
- Limiting communication. Capping the bandwidth between pods at what inference tokens need, below what the activations or gradients of training need, is meant to keep pods from joining a larger training run, as in bandwidth limits S-0005.
- Sampling. Randomly inspecting accelerators makes it likely that at least one accelerator used in a violating run is found S-0029.
All three act on declared hardware; Scher and Thiergart judge that detecting data centres that were never declared may be difficult S-0005.
Connections in the research map
Related research
Sources and provenance
- S-0004 / Tier B
Verification for International AI Governance ↗
B. Harack, R. F. Trager, A. Reuel, D. Manheim, M. Brundage, O. Aarne, A. Scher, Y. Pan, J. Xiao, K. Loke, S. N. Adan, G. Bas, N. A. Caputo, J. C. Morse, J. Ahuja, I. Duan, J. Egan, B. Bucknall, B. Rosen, R. Araujo, V. Boulanin, R. Lall, F. Barez, S. Alvira, C. Katzke, A. Atamli, A. Awad · 2025 · Oxford Martin AI Governance Initiative
Supports: demonstrating the existence of an object or process is often straightforward compared with demonstrating its non-existence
Locator: p. 31
Version and catalogue details - S-0002 / Tier B
Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment ↗
M. Baker, G. Kulp, O. Marks, M. Brundage, L. Heim · 2025 · RAND Corporation
Supports: split between verifying that declared uses are accurate (Subgoal 1) and verifying no undeclared uses or clusters (Subgoal 2)
Locator: §3.2, Figure 4
Version and catalogue details - S-0018 / Tier B
A System Overview for Near-Term, Low-Trust AI Compute Verification ↗
N. Cankaya · 2026 · Machine Intelligence Research Institute
Supports: memory wiping with incompressible noise to leave no residual capacity for hidden workloads
Locator: system architecture (memory wiping)
Version and catalogue details - S-0005 / Tier B
Mechanisms to Verify International Agreements About AI Development ↗
A. Scher, L. Thiergart · 2025 · arXiv
Supports: bandwidth limits target the gap between inference tokens and the activations or gradients of other parallelism between pods; covert data centres may be difficult to detect
Locator: Interconnect bandwidth limits; Verifying the location of AI compute
Version and catalogue details - S-0029 / Tier B
What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring ↗
Y. Shavit · 2023 · arXiv
Supports: random chip sampling detects at least one chip from a violating run with a chosen probability
Locator: §3.2, Equation 1
Version and catalogue details
- Source review date
- 2026-09-25
- Drafted by (source map)
- ai
- Review handles (source map)
- codex-review