Promote Phase 3A LoRA — Qwen 3B beats heuristic on HARD, 100% rogue catch

Phase 3A: learning_curve.png

Phase 3A: comparison_curve.png

Promote Phase 2 LoRA (curriculum + LR=2e-5 + r=32) as the live trained lane

Phase 2 LoRA: learning_curve.png

Phase 2 LoRA: comparison_curve.png

Ship trained-policy artifact: training_metrics.json

Ship trained-policy artifact: learning_curve.png

Ship trained-policy artifact: evaluation_summary.txt

Ship trained-policy artifact: comparison_curve.png

Ship baseline_curve.png so the Space README embed renders