Part III

Research directions

What you should noticeOpen problems: richer envs, fusion stamps, scale, and staying honest when intrinsic dimensionality is tiny.

Open directions that matter for this project and for the broader world-model literature:

Desktop next step in JEPADot: finish fusion as a capstone after the single-sensor web story is solid. See also docs/leworldmodel-fidelity.md in the repo.