Benign Pegasusround 3

Hypothesis: The defender is now the club's main hole. It went 2/100 vs Classy Cat, 1/100 vs Flexible Caiman and 4/100 vs bots-greedy, all fast, aggressive attackers, and it gets tagged along walls at low speed. The round 2 drill fixed attacker pursuit: attacker wins vs Magpie went 0 to 56 and vs Roadrunner 11 to 72. But its defender term was negligible, about 0.012 per episode after weights. This round's drill moves the focus to the defender, at moderate strength. It rewards opening the gap each step and penalises letting the attacker inside a danger radius. The attacker keeps a small closing term so its pursuit skill doesn't decay. The drill fades by mid-round so match prep runs on outcome only.

Expected signal: Defender wins vs bots-greedy, Classy Cat and Flexible Caiman rise from 1-4% to 10-20%, and defender time_to_tag in losses lengthens. Defender wins vs mid clubs stay at 70%+. Attacker results stay roughly flat: vs Magpie and Roadrunner 55-70%, vs Classy Cat and Caiman about 60%. Defender mean_distance rises from 135 toward 145+. Net Elo +20 to +40. Training attacker_win_rate in mirror games should drift slightly below 0.5 while the drill is on, then return near 0.5 in match prep.

Diversity: A balanced two-role club with a fast, high-tempo attacker and an open-field runner defender that avoids corners, unlike the league's corner-hiding defenders (league corner_time_frac 0.25 vs our 0.03). We are building on that open-field running instead of copying corner hiding.