diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
index db46114715d..6beb6e99e0e 100644
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@@ -54,7 +54,7 @@ After: the same request comes back with real token counts, so the dashboard show
 
 ## Affected release
 
-<!-- Only for a fix to a regression in a released or rc version (perf, memory, crash, or behavior): name the version it regressed in, e.g. "regression in v1.100.0" or "since v1.101.0-rc.1", and add the `backport-stable` label so the fix is cherry-picked onto the rc line before the stable is tagged. Drop the section otherwise -->
+<!-- Only for a fix to a regression in a released or rc version (perf, memory, crash, or behavior): name the version it regressed in, e.g. "regression in v1.100.0" or "since v1.101.0-rc.1". Add the `backport-stable` label only when the regression is a P0, meaning its Linear ticket is Urgent (a security hole however narrow, data loss, or a crash or outage for every user on that version), because every labeled PR must be cherry-picked onto the baking rc line before the stable can be tagged; every other regression fix ships in the next rc unlabeled. Drop the section otherwise -->
 
 ## Linear ticket