Some tasks are inferred based on the benchmarks list.
The benchmarks section lists all benchmarks using a given dataset or any of its variants. We use variants to distinguish between results evaluated on slightly different versions of the same dataset. For example, ImageNet 32⨉32 and ImageNet 64⨉64 are variants of the ImageNet dataset.
CTFW is a large annotated procedural text dataset in the cybersecurity domain (3154 documents). It is used to generate flow graphs from procedural texts.