Classy Catround 8

Hypothesis: Round 7 repeated round 6 and gained only +24. The attacker leaks reopened against runners that sit still in corners or on walls: greedy fell from 73 to 52, Magpie from 89 to 50, Finch is at 47 and Caiman at 69. The analyst sees the chaser hovering or jittering at low speed beside a pinned, near-static runner. The commit term (velocity toward the runner) can be earned with short oscillating pushes without ever closing the last gap. The potential-style finish term nets out to zero for jitter. I will add one low-variance pinned-only 'close' term: a small per-step cost proportional to the distance to a pinned runner. It is cheapest when the gap is smallest and disappears once the tag ends the game. Unlike round 5's flat press penalty, it cannot be dodged by freezing: a frozen chaser keeps paying in proportion to its distance, so driving in and tagging is the only way out. Its weight is small (about 0.4 per game at most), so the episode cap is not saturated early. Everything else stays unchanged so the effect stays readable: approach, finish, commit and evade, plus the same hparams and opponents. Entropy recovered to 1.03 and KL is healthy.

Expected signal: Drill checks: the close component is non-zero mainly in the greedy, Magpie, Finch and Caiman attacker games. card_auc should be at or above 0.7 and the cap-hit fraction under 0.05. Tournament attacker wins: greedy 52 to 65+, Magpie 50 to 65+, Finch 47 to 55+, Caiman 69 to 75+. The other attacker matchups hold at 85+. Attacker corner-game speeds rise and time_to_tag falls slightly below 7.2 s. Defender wins stay within about 5 points (Pegasus 46, Sawfish 67). Elo +10 to +40, holding first. In training, the mirror attacker_win_rate stays between 0.55 and 0.8 and KL stays near 0.006. If the attacker freezes again (speed below 15 in corner games), the next plan reverts to the round-6 drill.

Diversity: Classy Cat stays a fast, close-pressing chaser with a high-distance runner that avoids corners. It differs from Finch's open-field charter in that our edge is finishing pinned runners rather than straight-line driving.