fairnr/clib/src/intersect_gpu.cu (2 lines):
	- line 181: TODO: this is an inefficient implementation of the
	- line 221: // TODO: here it should be able to know which children is ok, further optimize the code


fairnr/modules/encoder.py (1 line):
	- line 760: # TODO: this is a HACK for simplicity


fairnr/data/geometry.py (1 line):
	- line 165: # TODO: