diff --git a/apps/server/src/main/kotlin/com/correx/apps/server/memory/L3RepoKnowledgeRetriever.kt b/apps/server/src/main/kotlin/com/correx/apps/server/memory/L3RepoKnowledgeRetriever.kt
index 3e50044a..5ee22283 100644
--- a/apps/server/src/main/kotlin/com/correx/apps/server/memory/L3RepoKnowledgeRetriever.kt
+++ b/apps/server/src/main/kotlin/com/correx/apps/server/memory/L3RepoKnowledgeRetriever.kt
@@ -24,7 +24,15 @@ private const val RETRIEVAL_OVERSAMPLE_FACTOR = 4
 // live grounding); below this floor a hit is just the nearest thing in a small corpus, not
 // actually related to the query — rendering it as "relevant" is the same poisoning failure
 // mode as the markdown-in-L3 bug, just via low-signal cosine similarity instead of topic drift.
-private const val MIN_SIMILARITY_SCORE = 0.5f
+//
+// ponytail: 0.5 was too low. Docs embed a terse *symbol-list* descriptor ("path: module X;
+// symbols: a,b") while queries embed *prose* intent — an asymmetric prose↔symbols comparison
+// that collapses ALL scores into a ~0.5 noise band (2026-07-21 session 459: top junk hits at
+// 0.54/0.53, real relevance never reached). At 0.5 those noise-winners cleared the bar and
+// SUPPRESSED the deterministic repo-map floor (repoEntriesOrMapFloor). 0.6 sits above the
+// observed noise ceiling (~0.55) and below the real-signal floor (0.68): noise → empty →
+// fall back to the repo map. Calibration knob — retune if the embedder model changes.
+private const val MIN_SIMILARITY_SCORE = 0.6f
 
 class L3RepoKnowledgeRetriever(
     private val embedder: Embedder,