A note about the generalisation of the C-tests
This is an incremental theoretical note on task performance measurement, with limited practical impact.
The paper explores a performance measure for all tasks using a difficulty function based on solution complexity, resulting in aggregations and decompositions that generalize C-tests.
In this exploratory note we ask the question of what a measure of performance for all tasks is like if we use a weighting of tasks based on a difficulty function. This difficulty function depends on the complexity of the (acceptable) solution for the task (instead of a universal distribution over tasks or an adaptive test). The resulting aggregations and decompositions are (now retrospectively) seen as the natural (and trivial) interactive generalisation of the C-tests.