DFA + residual-branch penalty test: seed=456, lam=0.01 ep 0: ||h_L||=8.890e+00 ||g_2||=9.971e-04 acc=0.0928 ep 1: ||h_L||=8.559e+02 ||g_2||=1.043e-05 eval_acc=0.3379 test_acc=0.3428 ep 10: ||h_L||=7.817e+03 ||g_2||=2.220e-06 eval_acc=0.3594 test_acc=0.3539 ep 20: ||h_L||=1.233e+04 ||g_2||=1.772e-06 eval_acc=0.3691 test_acc=0.3592 ep 30: ||h_L||=1.320e+04 ||g_2||=1.691e-06 eval_acc=0.3691 test_acc=0.3604 FINAL test acc: 0.3604 Compare to: DFA-vanilla (3-seed mean): 0.308 DFA-shallow (3-seed mean): 0.349 DFA-frozen (3-seed mean): 0.349 BP-trainable (3-seed mean): 0.609 Saved results/dfa_pen_short/dfa_pen_lam0.01_s456.json Saved results/dfa_pen_short/dfa_pen_lam0.01_s456.pt