feat(docs): add scenario provenance documentation

refactor(inference): enhance GPT system prompt and update policy initialization

feat(docs): enhance README and PITCH with detailed Viveka overview

feat(eval): add AQI evaluation scripts and reliability diagrams

docs: scenario JSON schema (single source of truth for both teammates)

post-keynote updates: deadline 17:00, Qwen2-0.5B primary, mentor checkpoints, pitch scripts