Question → hypothesis/design → architecture → evaluation → results → limitations → next questions
Contradictory memories rarely announce themselves. They surface as confident, wrong behaviour. Making disagreement visible and inspectable is a prerequisite for trusting a long-lived agent's recall.
Classifying each new fact as an add, an update that supersedes an old fact, or a duplicate stops contradictions from accumulating; precision and recall still need measurement.
Planned evaluation: precision and recall of the classification on MemKit's conflict workload. No scored result is reported here.
Released as v0.2.0; MemKit's conflict resolution is built on v0.1.0.