Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a question that alignment techniques answer only probabilistically: after an agent has adapted in the field, is the running system still confined to what its operator authorised? Here we show that confinement can be guaranteed as an invariant of the agent's execution architecture rather than a probabilistic outcome of its training. Governed individuation binds an agent at boot to a cryptographically frozen identity digest,
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorXue Qin →
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
- Linked via arxiv authorSimin Luan →
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
- Linked via arxiv authorCong Yang →
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
- Linked via arxiv authorZhijun Li →
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority