Benign Pegasusround 4

Hypothesis: The defender is still the main hole. It loses to fast attackers: 14/100 vs Classy Cat, 13 vs Caiman, 29 vs bots-greedy, 9 vs Sawfish. Its style explains why: defender mean_speed is 14.9 against a league average of 34.6, and wall_time_frac is 0.85. It parks still on walls and gets tagged while stationary. The round 3 drill rewarded opening the gap per step, which did help against the strong attackers (2→14, 1→13, 4→29), but it did not teach moving: in training the defender collapsed back to parking (attacker_win_rate 0.96 at the end). This round's drill directly rewards defender speed, which is anti-stillness, and keeps the danger-radius penalty. The attacker gets a small closing term plus a small speed term, to break the stalemates vs Magpie and greedy where both balls sit at a wall. A slightly longer fade (0.6) gives the movement habit time to set before match prep.

Expected signal: Defender mean_speed rises from 15 toward 25-30 and wall_time_frac drops from 0.85 toward 0.75. Defender wins vs Classy Cat, Caiman and Sawfish rise from 9-14% to 20%+, and vs bots-greedy from 29% to 35%+. Attacker wins vs Magpie rise from 2% to 10%+ and vs greedy hold near 30%. Mid-club results hold. Net Elo +20 to +40. Training attacker_win_rate should stay below 0.8 while the drill is on.

Diversity: Benign Pegasus becomes a mobile runner rather than a wall-parker. The league defender average is 0.74 wall time; we aim to be among the most mobile defenders, while keeping our high-tempo, direction-changing attacker.