CodSpeed: test_pickle_load[arm] is bimodal and randomly flags unrelated PRs #1110

test_pickle_load[arm] (added in #1092) is bimodal: it flips between ~1.6 ms and ~1.8 ms across commits that don't touch the pickle path at all, so with the 2% threshold it randomly paints unrelated PRs red.

Evidence from this week:

• Add callable support for decimal_format option #978 (decimal_format encoder option, head 045a25c vs main b36a4a1): flagged -10.05% (1.6 -> 1.8 ms), check red. The diff cannot affect struct pickling.
• Fix to_builtins with frozendict #1105 (to_builtins frozendict fix, head 5a54d59 vs main 8f7ac06): same benchmark reported +10.28% (1.8 -> 1.6 ms), check green (improvements don't gate).
• The baseline itself flipped between those two comparisons: main measured 1.6 ms at b36a4a1 (06-27) and 1.8 ms at 8f7ac06 (06-30), with exactly one commit in between (Add frozendict support for 3.15+ #1052, frozendict) that doesn't touch the pickle path either.

Since this is simulation mode (instruction counting), it's not run-to-run measurement noise: the benchmark appears sensitive to code layout/alignment in _core.c, so any code addition can toggle it between the two states. Related to the general variance discussion in #1075 and CodSpeedHQ/codspeed#409.

Options (all live in the CodSpeed dashboard, admin only - there's no repo-side config for this):

1. Set a per-benchmark regression threshold for test_pickle_load[arm] above the flip amplitude (say 15%). Keeps measuring, stops the false gating.
2. Ignore the benchmark entirely in CodSpeed.
3. The repo-wide "informational status check" toggle, which would also address the "CI looks perpetually broken" complaint from Fix crash on incorrect typing.ClassVar annotation #1097.

Option 1 seems the most targeted. Worth checking whether the sibling test_pickle_* benchmarks from #1092 show the same behavior before picking.