feat(example): add per-entity LLM evaluations for 985 WoN entities (S3.3)

Batch evaluation of all 988 entities via OpenRouter. 984 succeeded on
first pass; 3 failed (network errors). eval-summary --update-metrics
written with per_entity_mean=3.9556.

Viability dashboard: 6/6 PASS
  redundancy_ratio   0.0061  (max 0.10)
  coverage_ratio     0.6190  (min 0.40)
  coherence_comps    0.0000  (max 3)
  consistency_cycles 0.0000  (max 0)
  granularity_entropy 2.6748 (min 1.0)
  per_entity_mean    3.9556  (min 3.5)

Dimension breakdown (mean across 985 entities):
  definition_precision  3.62
  source_grounding      4.36
  domain_placement      4.56
  vsm_relevance         3.31
  explanatory_value     3.94

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

examples/infospace-with-history/output/evaluations/economic_system_best_practices.md

@@ -0,0 +1,65 @@
+---
+entity_slug: economic_system_best_practices
+evaluator: null
+evaluated_at: '2026-02-23T05:13:25.628492'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is vague and umbrella-like, listing broad categories ("free
+    trade, sound monetary policy, limited government intervention") without clearly
+    delineating what constitutes a distinct concept. It reads more like a summary
+    of policy recommendations rather than a precise conceptual definition.
+- name: source_grounding
+  value: 3.0
+  max_value: 5.0
+  rationale: While Smith does advocate for free trade and limited government intervention
+    throughout his work, the framing as "best practices" with "proven effectiveness"
+    imposes a modern analytical framework that doesn't reflect Smith's actual argumentative
+    approach. Smith argues from first principles about natural liberty rather than
+    from empirical "best practices."
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate since this entity attempts to synthesize
+    Smith''s broader policy recommendations across multiple economic domains. The
+    placement correctly recognizes this as a theoretical synthesis rather than a specific
+    mechanism.'
+- name: vsm_relevance
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity is too abstract and policy-oriented to map naturally to specific
+    VSM systems. It spans multiple systems (S4 intelligence about what works, S5 policy
+    identity) without clearly belonging to any particular one, making it VSM-neutral
+    at best.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity merely aggregates Smith's policy positions without illuminating
+    underlying mechanisms or structural relations. It names surface-level policy recommendations
+    rather than explaining why these practices emerge from Smith's theoretical framework
+    about natural liberty and market coordination.
+---
+
+# Evaluation: Economic System Best Practices
+
+## definition_precision — 2.0 / 5.0
+
+The definition is vague and umbrella-like, listing broad categories ("free trade, sound monetary policy, limited government intervention") without clearly delineating what constitutes a distinct concept. It reads more like a summary of policy recommendations rather than a precise conceptual definition.
+
+## source_grounding — 3.0 / 5.0
+
+While Smith does advocate for free trade and limited government intervention throughout his work, the framing as "best practices" with "proven effectiveness" imposes a modern analytical framework that doesn't reflect Smith's actual argumentative approach. Smith argues from first principles about natural liberty rather than from empirical "best practices."
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate since this entity attempts to synthesize Smith's broader policy recommendations across multiple economic domains. The placement correctly recognizes this as a theoretical synthesis rather than a specific mechanism.
+
+## vsm_relevance — 2.0 / 5.0
+
+This entity is too abstract and policy-oriented to map naturally to specific VSM systems. It spans multiple systems (S4 intelligence about what works, S5 policy identity) without clearly belonging to any particular one, making it VSM-neutral at best.
+
+## explanatory_value — 2.0 / 5.0
+
+This entity merely aggregates Smith's policy positions without illuminating underlying mechanisms or structural relations. It names surface-level policy recommendations rather than explaining why these practices emerge from Smith's theoretical framework about natural liberty and market coordination.