energysupport

the question

Does the masked-diffusion marginal-to-conditional energy proportionality constant depend only on sequence length and vocabulary size?

what came out

The masked-diffusion claim that the marginal-to-conditional kinetic-energy constant C1 depends only on (n,d) is false: C1 sums over the data marginal's support, so restricted support lowers it (4.000 to 1.917 as realizable support shrinks 27/27 to 3/27) while correlation alone does not. The energy-minimizing schedule still holds.

→ read the code and re-run it