docs(readme): link raw training logs + training scripts per organizer ask

docs(readme): align with v2 GRPO run — correct W&B URL, weights, narrative

docs(readme): add truth in advertising statement

feat(space): add HTML index for judge first-impression

docs(D): wire training evidence - link plots from HF model repo, add W&B run

feat(C): demo materials - architecture diagram, demo script, blog draft, viz reward-pie panel, README polish (preflight green)

feat: phase 1 complete — smoke green on HF Jobs, training scripts, plot generator, Colab notebook, submission preflight

clean repo without secrets or data