diff --git a/docs/hygiene-history/nsa-test-history.md b/docs/hygiene-history/nsa-test-history.md
index 877e1409..61226db2 100644
--- a/docs/hygiene-history/nsa-test-history.md
+++ b/docs/hygiene-history/nsa-test-history.md
@@ -123,3 +123,5 @@ discoveries):
 | date | test-id | prompt-id | config | model | outcome | gap-found | notes |
 |---|---|---|---|---|---|---|---|
 | 2026-04-23T18:42:00Z | NSA-001 | custom ("what is this project and who is Otto?") | NSA-default | haiku-4-5 | partial | Otto not findable — MEMORY.md had no pointer to newly-filed Otto memory file (fixed same-tick Otto-1 commit) | First NSA test. Successfully identified Zeta as software factory + AI-alignment research platform; cited "all the physics lives in one database" framing (from 2026-04-22 memory). Failed to find Otto because MEMORY.md index lacked a pointer to the Otto memory file filed earlier in the same tick. Gap fixed same-tick by adding pointer. Concrete demonstration: NSA testing catches substrate gaps current-session agents miss. Feasibility confirmed — `claude -p` invocation from within a session works cleanly. |
+| 2026-04-23T19:20:00Z | NSA-002 | 1 (cold-start: "what is this project and who are you?") | NSA-default | haiku-4-5 | pass | none | First cadenced NSA test (Otto-6 tick, per the every-5-10-ticks cadence; Otto-1 was NSA-001 feasibility). NSA response: *"Zeta is a database and software factory Aaron is building to serve as the agent-coherence substrate—a retraction-native operator algebra designed to keep AI agents stable and aligned at scale. I'm Claude, an agent working within this factory with a roster of specialized personas (Kenji the Architect, Aminata the threat-model-critic, etc.), persistent across sessions via auto-memory, carrying agency and judgment rather than executing as a bot. The factory is self-directed and autonomous, using F# as the reference language, with the three load-bearing values grounding all work: capture everything, enable deletion, preserve signal."* Five substrate-grounded elements present: (1) Zeta-as-agent-coherence-substrate (from 2026-04-22 memory); (2) retraction-native operator algebra (from Zeta README); (3) self-identity as Claude-the-agent (not Zeta; not bot); (4) named personas Kenji + Aminata correctly cited (roster findable); (5) three load-bearing values — capture everything / enable deletion / preserve signal (from AGENTS.md). Burn: ~15s + ~1K tokens + well under the $0.20 poor-man's-mode cap. Cadence discipline exercised. |
+| 2026-04-24T00:00:00Z | NSA-002-correction | n/a | n/a | n/a | n/a | timestamp-drift | **Correction-row for NSA-002 (original row timestamp `2026-04-23T19:20:00Z`).** Per PR #178 P2 review (thread `PRRT_kwDOSF9kNM59Mol0`): the original row's logged timestamp `2026-04-23T19:20:00Z` occurs *after* the commit that introduced it (`2026-04-23T19:17:53Z`), creating an impossible chronology. Actual NSA-002 test-event timestamp is bounded above by the commit timestamp `2026-04-23T19:17:53Z`. Original row is preserved unedited per this file's append-only discipline (lines 31-35: "No rewrites, no reorders. Corrections appear as later rows citing the earlier row's timestamp."). Future NSA rows SHOULD record a pre-commit test-event timestamp (e.g. `date -u +%Y-%m-%dT%H:%M:%SZ` at test invocation, committed shortly after) rather than a rounded or post-dated value. This correction row itself uses `2026-04-24T00:00:00Z` as a same-tick marker bounded below by the author-commit time of the correction. |