HypergraphConv raises index out of bounds when hyperedge ID exceeds number of nodes

[strikene]

I'm learning HypergraphConv to use my own data.
Torch=2.71+CU11 torch-geometric=2.6.1
On x = self.hconv1(data.x, data.hyperedge_index)
got error index 10 is out of bounds for dimension 0 with size 10
I've uploaded my code and test data as attachments.
I don't know if this is a design or some other mistake on my part

I manually build hyperedges so that the number exceeds the number of nodes and I get an error
Once I manually build the hyperedge so that it is less than the number of nodes (10), I don't get the error anyway
Demo.zip