fix: target_encoder.py — respect config.jepa_loss_fn (smooth_l1/mse/cosine) instead of hardcoded MSE

fix: mr_jepa.py — proper evidence gate disable via gate_type (no lambda hack), init ablation flags from config, update docstrings to current stack

fix: backbones.py — DINOv3 via timm + Qwen3-Embedding-0.6B, add get_transform(), proper layer unfreezing for both architectures

Remove __pycache__ files

Initial MR-JEPA codebase: architecture, training, evaluation, and tests