Status: IN
The human cannot track what the LLM currently has in context. Context windows are opaque and compaction destroys justification networks. EEM solves this via visibility and persistence — the human can always inspect the current belief state regardless of what the model has in context.
Source: repo:beliefs-pi/CLAUDE.md
Depends on (SL): eem-external
Depends on (SL): eem-external, context-opacity, compaction-destroys-networks