The three other conditions were predicted to prevent chunking processes, either because the interleaved processing task did not allow any chunking process to occur or because the noncompressible material inherently limited the chunkability of information.
![backward digit span test items pdf backward digit span test items pdf](https://originclimate.org/images/digit-span-test-instructions-3.jpg)
We predicted an interaction between the types of tasks and chunkability/compressibility, supporting a single higher span for the condition in which a simple span task was combined with chunkable items. To manipulate the chunkability of the stimulus lists, our method involved a measure of their compressibility, i.e., the extent to which a pattern exists that can be detected and used as a basis of chunk formation. It follows that the respective spans of these two types of tasks could be equal (at around 4 ± 1) if stimulus lists exclusively used nonchunkable stimulus items. One possible reason for the higher span of simple span tasks is that participants can take advantage of the spare time to chunk multiple items together to form fewer independent units, approximating 4 ± 1 chunks. Consequently, the average span is usually lower (4 ± 1 items) than in simple span tasks (7 ± 2 items). Complex working memory span tasks were designed to engage multiple aspects of working memory and impose interleaved processing demands that limit the use of mnemonic strategies, such as chunking.