docs: README only lists 3 trained systems; drop tier-3 held-out claims and stale example

docs: drop per-component reward breakdown chart and bullets

openenv push: sync full repo

Upload folder using huggingface_hub

Update blog link to blog.md

Fix links table: absolute URLs for blog, notebook, checkpoint

Update plots, fix README table fmt, update training result observations

ui: status banner + endpoint guide for physix-infer cold-start

Upload folder using huggingface_hub

initial commit