# Phase C+20 cold-vs-cold result (2026-05-14)

## No engine changes

C+20 produces NO source modifications to either `xenia-rs` or
`xenia-canary`. The session was a verify-only iteration concluding
in an escalation decision (see `investigation.md`).

## Matched-prefix table (vs C+19 baseline)

| chain                          | C+19    | C+20    | delta |
|--------------------------------|---------|---------|-------|
| canary tid=6 → ours tid=1 main | 104,606 | 104,606 | 0     |
| canary tid=4 → ours tid=11     | 11      | 11      | 0     |
| canary tid=7 → ours tid=2      | 32      | 32      | 0     |
| canary tid=12 → ours tid=7     | 3       | 3       | 0     |
| canary tid=14 → ours tid=9     | 41      | 41      | 0     |
| canary tid=15 → ours tid=10    | 16      | 16      | 0     |

## Cold-stable digest

`e1dfcb1559f987b35012a7f2dc6d93f5` — unchanged from C+13/C+15-α
/C+16/C+17/C+18/C+19 (no source changes; digest cannot drift).

## Phase B image hash

`ea8d160e9369328a5b922258a92113efb8d7ce3e1a5c12cc521e375985c91c18` —
unchanged (no source changes).

## Tests

Kernel: 204 PASS (unchanged from C+19, no test additions).

## Canary non-determinism observation (NEW — RE class #32)

Cross-validated across 3 fresh canary cold jsonls
(`canary-jitter-{1,2,3}.jsonl` from C+19 jitter probe, all wiped-cache
cold). At tid=6 idx 104,606:

- jitter-1: `wait.begin sid=75ae880ec432eb36 timeout=-1`
- jitter-2: `kernel.return RtlEnterCriticalSection rv=0`  ← matches ours
- jitter-3: `kernel.call RtlLeaveCriticalSection` (offset shift; the
  wait.begin moved to idx 104,603 with a different SID)

The contention pattern in canary's `RtlEnterCriticalSection` is
host-scheduler-dependent. The matched-prefix metric is unreliable in
this region.

## Outcome

ESCALATE to scheduler-determinism track (separate session, larger
scope).