diff --git a/README.md b/README.md
index 81aa5b4..c3597c1 100644
--- a/README.md
+++ b/README.md
@@ -437,6 +437,7 @@ This benchmark tests **LLM comprehension and data retrieval accuracy** across di
 Eleven datasets designed to test different structural patterns and validation capabilities:
 
 **Primary datasets:**
+
 1. **Tabular** (100 employee records): Uniform objects with identical fields – optimal for TOON's tabular format.
 2. **Nested** (50 e-commerce orders): Complex structures with nested customer objects and item arrays.
 3. **Analytics** (60 days of metrics): Time-series data with dates and numeric values.
@@ -445,6 +446,7 @@ Eleven datasets designed to test different structural patterns and validation ca
 6. **Nested Config** (1 configuration): Deeply nested configuration with minimal tabular eligibility.
 
 **Structural validation datasets:**
+
 7. **Control**: Valid complete dataset (baseline for validation)
 8. **Truncated**: Array with 3 rows removed from end (tests `[N]` length detection)
 9. **Extra rows**: Array with 3 additional rows beyond declared length
diff --git a/benchmarks/results/retrieval-accuracy.md b/benchmarks/results/retrieval-accuracy.md
index 5a9d02d..868103b 100644
--- a/benchmarks/results/retrieval-accuracy.md
+++ b/benchmarks/results/retrieval-accuracy.md
@@ -278,6 +278,7 @@ This benchmark tests **LLM comprehension and data retrieval accuracy** across di
 Eleven datasets designed to test different structural patterns and validation capabilities:
 
 **Primary datasets:**
+
 1. **Tabular** (100 employee records): Uniform objects with identical fields – optimal for TOON's tabular format.
 2. **Nested** (50 e-commerce orders): Complex structures with nested customer objects and item arrays.
 3. **Analytics** (60 days of metrics): Time-series data with dates and numeric values.
@@ -286,6 +287,7 @@ Eleven datasets designed to test different structural patterns and validation ca
 6. **Nested Config** (1 configuration): Deeply nested configuration with minimal tabular eligibility.
 
 **Structural validation datasets:**
+
 7. **Control**: Valid complete dataset (baseline for validation)
 8. **Truncated**: Array with 3 rows removed from end (tests `[N]` length detection)
 9. **Extra rows**: Array with 3 additional rows beyond declared length
diff --git a/benchmarks/src/report.ts b/benchmarks/src/report.ts
index 0adafa6..4803115 100644
--- a/benchmarks/src/report.ts
+++ b/benchmarks/src/report.ts
@@ -284,6 +284,7 @@ This benchmark tests **LLM comprehension and data retrieval accuracy** across di
 Eleven datasets designed to test different structural patterns and validation capabilities:
 
 **Primary datasets:**
+
 1. **Tabular** (${tabularSize} employee records): Uniform objects with identical fields – optimal for TOON's tabular format.
 2. **Nested** (${nestedSize} e-commerce orders): Complex structures with nested customer objects and item arrays.
 3. **Analytics** (${analyticsSize} days of metrics): Time-series data with dates and numeric values.
@@ -292,6 +293,7 @@ Eleven datasets designed to test different structural patterns and validation ca
 6. **Nested Config** (${nestedConfigSize} configuration): Deeply nested configuration with minimal tabular eligibility.
 
 **Structural validation datasets:**
+
 7. **Control**: Valid complete dataset (baseline for validation)
 8. **Truncated**: Array with 3 rows removed from end (tests \`[N]\` length detection)
 9. **Extra rows**: Array with 3 additional rows beyond declared length
diff --git a/docs/guide/benchmarks.md b/docs/guide/benchmarks.md
index c6c6460..e0d2a37 100644
--- a/docs/guide/benchmarks.md
+++ b/docs/guide/benchmarks.md
@@ -294,6 +294,7 @@ This benchmark tests **LLM comprehension and data retrieval accuracy** across di
 Eleven datasets designed to test different structural patterns and validation capabilities:
 
 **Primary datasets:**
+
 1. **Tabular** (100 employee records): Uniform objects with identical fields – optimal for TOON's tabular format.
 2. **Nested** (50 e-commerce orders): Complex structures with nested customer objects and item arrays.
 3. **Analytics** (60 days of metrics): Time-series data with dates and numeric values.
@@ -302,6 +303,7 @@ Eleven datasets designed to test different structural patterns and validation ca
 6. **Nested Config** (1 configuration): Deeply nested configuration with minimal tabular eligibility.
 
 **Structural validation datasets:**
+
 7. **Control**: Valid complete dataset (baseline for validation)
 8. **Truncated**: Array with 3 rows removed from end (tests `[N]` length detection)
 9. **Extra rows**: Array with 3 additional rows beyond declared length