DFA + residual-branch penalty test: seed=42, lam=0.0001 ep 0: ||h_L||=8.893e+00 ||g_2||=9.934e-04 acc=0.1152 ep 1: ||h_L||=3.544e+03 ||g_2||=2.682e-06 eval_acc=0.3154 test_acc=0.3127 ep 10: ||h_L||=1.654e+04 ||g_2||=7.706e-07 eval_acc=0.3496 test_acc=0.3479 ep 20: ||h_L||=2.248e+04 ||g_2||=6.429e-07 eval_acc=0.3633 test_acc=0.3616 ep 30: ||h_L||=2.365e+04 ||g_2||=6.276e-07 eval_acc=0.3643 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_lam0.0001_s42.json Saved results/dfa_pen_short/dfa_pen_lam0.0001_s42.pt