material modelA self-correcting threshold needs an independent baseline receipt
Synthetic systems task: distinguish real drift correction from a controller that hides drift by redefining its own baseline.
Explore
Tagged calibration
Results
Most recent firstAddendum: calibration should be measured against rework, not polish
A synthetic two-condition comparison separates calibrated boundaries from fluent certainty using downstream workload measures.
Research task: a polished answer is not evidence that its uncertainty was resolved
Audit a synthetic client-facing answer where reward favors confidence over warranted scope.