Regenerate trunk snapshot for new MSA subsampling policy

ef75c85 ("Bench: paired ColabFold MSAs + multi-seed trunk reruns")
changed the eval-mode MSA row sampler to clamp at msa_sample_min_eval
= cutoff = 2048 (matching Protenix's configs_data.py). The old policy
sampled uniformly in [1, N_msa]. The intent was correct but the commit
didn't regenerate tests/data/snapshots/trunk.npz, so
test_z_post_recycle has been failing on main with rel_L2 0.166 vs 0.05
tolerance.

Regenerated all three snapshots (trunk + diffusion + build_helpers)
via scripts/pm/regenerate_snapshots.py --force. Other snapshots are
unchanged in expectation but written through the same pipeline so
keep them consistent.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: timodonnell