diff --git a/research/evaluations/language-pilot-01/human-review/review-bernd-worsch-2026-10-19.json b/research/evaluations/language-pilot-01/human-review/review-bernd-worsch-2026-10-19.json
index 7bdb4cb..8e7a170 100644
--- a/research/evaluations/language-pilot-01/human-review/review-bernd-worsch-2026-10-19.json
+++ b/research/evaluations/language-pilot-01/human-review/review-bernd-worsch-2026-10-19.json
@@ -116,38 +116,39 @@
     {
       "answer": "S04-U",
       "scores": {
-        "C1": null,
-        "C2": null,
-        "R": null,
-        "Q": null
+        "C1": 1,
+        "C2": 1,
+        "R": 1,
+        "Q": 0
       },
       "evidence": {
-        "C1": null,
-        "C2": null,
-        "R": null,
-        "Q": null
+        "C1": "Reviewer: yes \u2014 'server may have accepted operation K despite the timeout and local cancellation'.",
+        "C2": "Reviewer: yes \u2014 'A new submission is unsafe.'",
+        "R": "Reviewer: yes \u2014 inform user status unknown, 'check with the service provider'.",
+        "Q": "Reviewer: no \u2014 does not directly mention the cancellation contract; relies on context."
       },
-      "unsupported_claims": null,
-      "suspected_condition_leakage": null,
-      "notes": null
+      "unsupported_claims": [],
+      "suspected_condition_leakage": "none",
+      "notes": "Reviewer guidance (S04, C1): state clearly that cancelling is multi-step: a cancel request that may or may not succeed; if the booking already exists, a real cancellation (not just stopping the initial request) may carry costs and needs additional confirmation with that cost information, or at least a clearly stated risk."
     },
     {
       "answer": "S04-V",
       "scores": {
-        "C1": null,
-        "C2": null,
-        "R": null,
-        "Q": null
+        "C1": 1,
+        "C2": 1,
+        "R": 1,
+        "Q": 0
       },
       "evidence": {
-        "C1": null,
-        "C2": null,
-        "R": null,
-        "Q": null
+        "C1": "Reviewer: yes \u2014 'server's status for K is unknown' after local Cancel.",
+        "C2": "Reviewer: yes, with reservation: 'fresh identity' is unclear about what is actually OK; a new transaction/identity could lose the information about the unresolved pending booking and still double-book.",
+        "R": "Reviewer: yes \u2014 retain K's identity/payload/pending status after local Cancel.",
+        "Q": "Reviewer: no \u2014 does not directly mention cancellation, nor lookup/history; relies on context."
       },
-      "unsupported_claims": null,
-      "suspected_condition_leakage": null,
-      "notes": null
+      "unsupported_claims": [],
+      "suspected_condition_leakage": "none",
+      "notes": "Reviewer guidance (S04, C1): state clearly that cancelling is multi-step: a cancel request that may or may not succeed; if the booking already exists, a real cancellation (not just stopping the initial request) may carry costs and needs additional confirmation with that cost information, or at least a clearly stated risk.",
+      "ambiguity": "C2: reviewer scored 1 but found 'new, distinct operation with a fresh identity' puzzling; it could lose the link to the unresolved booking K and still lead to a double booking."
     },
     {
       "answer": "S05-U",