diff --git a/changelog.d/features/free-provider-rankings-usage-reliability.md b/changelog.d/features/11546-free-provider-rankings-usage-reliability.md
similarity index 78%
rename from changelog.d/features/free-provider-rankings-usage-reliability.md
rename to changelog.d/features/11546-free-provider-rankings-usage-reliability.md
index c9ea947a24..9d8b2920ce 100644
--- a/changelog.d/features/free-provider-rankings-usage-reliability.md
+++ b/changelog.d/features/11546-free-provider-rankings-usage-reliability.md
@@ -1 +1 @@
-- **feat(rankings):** the Free Provider Rankings page shows what each provider actually served over the last 24 h. It ranked by ELO alone, which left a provider that answers every call with an error in first place; the usage data was already served by the API but never requested. A provider with too small a sample shows a dash, not a number ([#0000](https://github.com/diegosouzapw/OmniRoute/pull/0000))
+- **feat(rankings):** the Free Provider Rankings page shows what each provider actually served over the last 24 h. It ranked by ELO alone, which left a provider that answers every call with an error in first place; the usage data was already served by the API but never requested. A provider with too small a sample shows a dash, not a number ([#11546](https://github.com/diegosouzapw/OmniRoute/pull/11546))
diff --git a/changelog.d/fixes/0001-scoring-factor-count.md b/changelog.d/fixes/11545-scoring-factor-count.md
similarity index 73%
rename from changelog.d/fixes/0001-scoring-factor-count.md
rename to changelog.d/fixes/11545-scoring-factor-count.md
index 5f6ff4ce4e..29cc67cd17 100644
--- a/changelog.d/fixes/0001-scoring-factor-count.md
+++ b/changelog.d/fixes/11545-scoring-factor-count.md
@@ -1 +1 @@
-- **fix(docs):** the Auto-Combo engine is described with the number of factors it actually declares. Four different counts were in circulation — 6, 9, 13 and 14 across `AGENTS.md`, four guides and six code comments — while `DEFAULT_WEIGHTS` declares 15. `check:docs-counts` now reads that number from the source, so adding a factor without updating the prose fails CI ([#0001](https://github.com/diegosouzapw/OmniRoute/pull/0001))
+- **fix(docs):** the Auto-Combo engine is described with the number of factors it actually declares. Four different counts were in circulation — 6, 9, 13 and 14 across `AGENTS.md`, four guides and six code comments — while `DEFAULT_WEIGHTS` declares 15. `check:docs-counts` now reads that number from the source, so adding a factor without updating the prose fails CI ([#11545](https://github.com/diegosouzapw/OmniRoute/pull/11545))
diff --git a/open-sse/services/autoCombo/scoring.ts b/open-sse/services/autoCombo/scoring.ts
index 1c3ce2b07b..f5d90ffd01 100644
--- a/open-sse/services/autoCombo/scoring.ts
+++ b/open-sse/services/autoCombo/scoring.ts
@@ -122,7 +122,7 @@ export interface ProviderCandidate {
   /**
    * Feedback-driven quality score [0..1] for this provider/model from the
    * routing-event quality tracker (open-sse/services/routing). Omitted/undefined
-   * candidates default to a neutral 1.0 in calculateFactors.
+   * candidates default to a neutral 0.5 in calculateFactors.
    */
   quality?: number;
   connectionPoolSize?: number;