faeval.git/README_experiments.md, branch master Unnamed repository; edit this file 'description' to name the repository. Add final report, plots, experiment guide, and complete NOTE.md 2026-03-24T00:46:08+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-03-24T00:46:08+00:00 32123cb36ae9521f60c9b6f67458b931b6540ef2 All experiments complete: - Toy LQ: credit bridge matches state bridge (~0.94 costate cosine) - CIFAR-10: credit bridge (29.6%) comparable to DFA (30.0%), both beat state bridge (18.5%) - State bridge confirms core hypothesis: perfect state prediction != useful credit - Terminal gradient matching is essential for credit bridge 
All experiments complete:
- Toy LQ: credit bridge matches state bridge (~0.94 costate cosine)
- CIFAR-10: credit bridge (29.6%) comparable to DFA (30.0%), both beat state bridge (18.5%)
- State bridge confirms core hypothesis: perfect state prediction != useful credit
- Terminal gradient matching is essential for credit bridge