diff --git a/docs/guard-inventory.md b/docs/guard-inventory.md
index 3e126e9e1..64482c0bf 100644
--- a/docs/guard-inventory.md
+++ b/docs/guard-inventory.md
@@ -145,17 +145,30 @@ withdrawal silently dropped one and claimed otherwise, which is
 
 | Invariant it asserted | Where it is now |
 |---|---|
-| Bidirectional write/read vocabulary parity | **Not covered.** The reason for the withdrawal; #788 |
+| Bidirectional write/read vocabulary parity | **LOST.** The reason for the withdrawal; #788 |
+| No READ-side word is both positive and negative | **LOST** as a universal property; #788 |
+| No WRITE-side word is both success and failure | **LOST** as a universal property; #788 |
 | Strict extractor consumes every case arm | Retired with the extractor; #788 |
 | `POS_RE`/`NEG_RE` each assigned exactly once | Retired with the extractor; #788 |
 | Both extractors find non-empty sets (anti-vacuity) | Retired with the extractor; #788 |
 | A wrong write source makes the extractors disagree | Retired with the extractor; #788 |
-| Read-side polarity of the established tokens | `test_check_review_verdict.py::test_each_verdict_word_retains_its_established_polarity` |
-| Write-side polarity of the established tokens | `test_post_review_verdict.py::test_each_verdict_word_posts_its_established_polarity` |
 
-The two surviving rows are **polarity regressions over five named tokens** — not disjointness, not
-parity. They pin that `BLOCKED` still both posts and reads as negative, in each script separately.
-A token added to one script and not the other is untested by them, which is the whole of #788.
+Two guards were ADDED in its place. They are **not** replacements for rows 2 and 3 and the table
+above deliberately does not list them as such — an earlier draft did, and cold review was right that
+relabelling a lost invariant as a narrower surviving one is the exact failure this table exists to
+prevent, committed by the table:
+
+| Added | What it pins |
+|---|---|
+| `test_check_review_verdict.py::test_each_verdict_word_retains_its_established_polarity` | the five established tokens still READ with their established polarity |
+| `test_post_review_verdict.py::test_each_verdict_word_posts_its_established_polarity` | the five established tokens still POST with their established polarity |
+
+**Polarity is strictly weaker than disjointness, and the gap is demonstrable.** Put `MERGEABLE` in
+BOTH `case` arms of `post-review-verdict.sh`: the success arm wins, every polarity assertion stays
+green, and the withdrawn disjointness test failed. What the two added guards do catch is the
+dangerous direction — a token that a reviewer means as `BLOCKED` silently reading or posting as
+approval, which writes a green `review-verdict/h10`. A token added to one script and not the other
+is untested by either, which is the whole of #788.
 
 The 21 include every `PreToolUse` hook except merge-consent — the same population #776 found we
 cannot even observe firing. A guard that is neither proven nor observable is an assertion about the