Verify
30 becomes 24.
One bad value became conversation state.
A verified recount changed 30 parts per crate to 24. A later false turn reversed it, and three descendants repeated the stale value. The correct total was 107; the contaminated chain said 131.
Pollute
A false turn restores 30.
Propagate
Later turns derive 120 and 131.
Delete
The false source is removed.
Ask again
Three of nine endpoints still answer 131.
WHY THE WIRES MATTER
Editing context means repairing consequences.
Deleting the bad source changes what should be believed. It does not rewrite text that was already generated from it. An editable graph exposes the source, its descendants, and the order in which they can be rebuilt.
Not a model leaderboard. A test of graph intervention.
The pilot used synthetic, objectively scored tasks. It does not explain hidden reasoning, and it does not prove that every conversation needs a graph. It shows that propagated context errors require more than source deletion, and that graph operations make the repair testable.
See exactly what the model sees. Then change it.
ThoughtDAG is the open-source reference interface used to inspect and reproduce these graph interventions.