chore: Rename Dockerfile to fix HF Space deploy, and clean up AI slop

Update evaluation results, fix Gradio compatibility, and resolve sandbox execution path on macOS

chore: normalize dataset inputs and fix mergekit dependency for TRL 0.14.0

Add interactive Gradio demo at /demo in env Space

Update: Started making changes for the hackathon

Fix: Changed environment variables and added validator

Fix: Final submission cleanup, unified identity and integrity markers

Update: Made refinements to the project

Fix: Changed scores range

fix: score floor for medium grader, add root and tasks endpoints

Cleaner code and logic improvement

docs: final professional polish and code sanitization

made changes to server.py

complete project

Added testing files

first commit