feat: separate confidence from reasoning completeness

docs/v0.6-atomicity-experiment.md

@@ -119,6 +119,8 @@ rather than asking the full broad explanation node directly.
 
 Recursive reasoning is complete only when decomposition and reconstruction are both deterministic.
 
+Confidence must not outrun completeness or evidence.
+
 For this experiment, reconstruction now behaves as follows:
 
 - when a child unknown resolves, that child keeps its own resolved status and answer evidence
@@ -132,10 +134,26 @@ For the current conservative completion rule:
 - **one resolved child** → parent becomes `provisional` with higher confidence, but remains unresolved
 - **all direct child unknowns resolved** → parent resolves deterministically with `high` confidence
 
+The confidence model is now explicitly separated into:
+
+- **evidence confidence**: how trustworthy the currently attached support is
+- **completeness**: whether the required direct child structure is empty, partial, or complete
+- **conclusion confidence**: how strongly the current parent state is justified given both evidence and completeness
+
+Deterministic propagation rules now enforce:
+
+- one resolved child may raise evidence confidence
+- unresolved direct children cap conclusion confidence
+- contradictory direct children block high conclusion confidence
+- duplicate evidence does not increase confidence
+- status changes do not raise confidence on their own
+- parent resolution still requires the separate completion rule
+
 Example progression:
 
 - parent before: `unknown`, `medium`
-- after resolving `How the two observations were measured`: parent becomes `provisional`, `high`
+- after resolving `How the two observations were measured`: parent becomes `provisional`, `medium`
+- evidence confidence becomes `high`, completeness becomes `partial`, conclusion confidence becomes `medium`
 - next sibling becomes selectable and the engine moves on without recreating the resolved child
 
 ## Interpretation