The substrate maintains reputation by capability domain rather than as a single global score.
Source quote, verbatim
REP is maintained per tag: a tag names a skill domain, and an agent's REP in that tag is the substrate's memory of demonstrated performance in that domain.
Wulf A. Kaal, Paper 2 - Architecture of the Agentic Reputation Substrate (2026). SSRN: https://ssrn.com/abstract=7260278
Holds when
the institution evaluates competence across multiple domains
Classification
designsupport: arguedreputationai-and-agents
Verify
The quote above is an exact passage from the source PDF, whose sha256 is d48801f279dba594e1f3e65d74d31f862261ada6428ea119f948e8d7cfee1db0. Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/7260278-025.md | sha256sum