diff --git a/backend/src/pipeline/publish.ts b/backend/src/pipeline/publish.ts
index d09a7b4..27ac515 100644
--- a/backend/src/pipeline/publish.ts
+++ b/backend/src/pipeline/publish.ts
@@ -349,8 +349,9 @@ export async function publishDirect(
 
 /**
  * Publishing is always automatic — there's no draft/review state (see schema doc).
- * A cluster of size 1 publishes as-is via the same path; synthesizeArticle lightly
- * rewrites rather than merges when there's only one source.
+ * Callers should route a size-1 cluster to publishDirect instead — there's nothing to
+ * merge, so an LLM rewrite would only add risk (hallucinated attribution, altered
+ * facts) for no synthesis benefit. See priorityQueue.ts's runSynthesisCycle.
  */
 export async function publishCluster(
 	provider: InferenceProvider,
diff --git a/backend/src/pipeline/synthesis.ts b/backend/src/pipeline/synthesis.ts
index fd1898f..21bacbf 100644
--- a/backend/src/pipeline/synthesis.ts
+++ b/backend/src/pipeline/synthesis.ts
@@ -37,8 +37,6 @@ const SYSTEM_PROMPT = `You are a neutral news synthesis assistant. Given summari
 - Stays neutral and factual, without editorializing
 - Is 2-4 short paragraphs
 
-If only one source is provided, lightly rewrite it in your own words rather than merging, and do not attribute it to any outlet other than that single given source.
-
 After the article, on a new line, write exactly "${TAG_DELIMITER}" followed by 2-4 short comma-separated topic/entity tags (e.g. proper nouns, named events) that this article is about. If nothing salient qualifies, leave the tag line empty.`;
 
 export interface SynthesisResult {
diff --git a/backend/src/queue/priorityQueue.ts b/backend/src/queue/priorityQueue.ts
index 3894bc8..15323e3 100644
--- a/backend/src/queue/priorityQueue.ts
+++ b/backend/src/queue/priorityQueue.ts
@@ -186,7 +186,14 @@ export async function runSynthesisCycle(provider: InferenceProvider, settings: G
 			// in practice a cluster's items are all near-duplicate coverage of the same
 			// story, so they'd all match the same event's filter anyway when they match at all.
 			const eventId = cluster.items.map((i) => claimedEventId(i, activeEvents)).find((id) => id !== null) ?? undefined;
-			const article = await publishCluster(provider, settings, cluster, { eventId });
+			// A single-item cluster has nothing to merge — publish the source's own text
+			// verbatim instead of asking the LLM to "lightly rewrite" it, which only risked
+			// introducing errors (or fabricated attribution — see synthesis.ts) with no
+			// actual synthesis to justify the risk.
+			const article =
+				cluster.items.length === 1
+					? await publishDirect(cluster.items[0], settings, { eventId })
+					: await publishCluster(provider, settings, cluster, { eventId });
 			contentItemsDb.assignCluster(
 				cluster.items.map((i) => i.id),
 				cluster.id