Sync to local main (commit 1e292cf): post-hackathon blog updates

Polish Viveka blog with references and minor fixes

Add research-context references to Viveka blog

feat(submission): trained Llama-3B sealed eval + leaderboard PNG + Gradio fix

feat(eval): add baseline evaluation files for Claude and GPT models

feat(submission): canonical OpenEnv layout + loss curves + Llama-3B baseline

docs(readme): audit fixes + Llama 1B sealed eval + 3-architecture results

feat(inference, train, eval): enhance user prompt structure with memory orchestration fields

feat(eval): add xkcd / hand-drawn style option to reward curve plot

feat(eval): combined two-architecture reward curve plot (rubric headline)

feat(kaggle): drop-in Kaggle training notebook + pin mcp>=1.10

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

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