DFA + residual-branch penalty test: seed=42, lam=0.01 ep 0: ||h_L||=8.893e+00 ||g_2||=9.934e-04 acc=0.1152 ep 1: ||h_L||=7.888e+02 ||g_2||=1.141e-05 eval_acc=0.3359 test_acc=0.3353 ep 10: ||h_L||=7.251e+03 ||g_2||=2.304e-06 eval_acc=0.3662 test_acc=0.3517 ep 20: ||h_L||=1.137e+04 ||g_2||=1.814e-06 eval_acc=0.3730 test_acc=0.3649 ep 30: ||h_L||=1.216e+04 ||g_2||=1.757e-06 eval_acc=0.3750 test_acc=0.3593 FINAL test acc: 0.3593 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_s42.json Saved results/dfa_pen_short/dfa_pen_lam0.01_s42.pt