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/adulteration_of_coin_standard.md

@@ -0,0 +1,64 @@
+---
+entity_slug: adulteration_of_coin_standard
+evaluator: null
+evaluated_at: '2026-02-23T00:19:36.700072'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly distinguishes adulteration from other forms of
+    currency debasement by specifying the covert mixing of base metals while maintaining
+    weight and appearance. It precisely captures the deceptive nature that differentiates
+    this practice from open devaluation methods.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This concept is directly grounded in Smith's text from Book V, Chapter
+    3, where he explicitly discusses adulteration as a fraudulent currency practice
+    involving secrecy and mint official complicity. The entity accurately reflects
+    Smith's actual discussion rather than introducing external concepts.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Regulation" domain assignment is highly appropriate since adulteration
+    represents a regulatory failure in monetary oversight and control. This practice
+    directly concerns the government's role in maintaining currency integrity and
+    preventing fraudulent monetary manipulation.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it represents
+    a breakdown in monetary control systems, and potentially to S2 (coordination)
+    regarding the maintenance of currency standards. The regulatory and oversight
+    aspects make it naturally relevant to VSM system functions.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: The entity illuminates an important mechanism of currency debasement
+    that differs structurally from open devaluation, helping explain how monetary
+    systems can be undermined through deceptive practices. It reveals the institutional
+    vulnerabilities that enable covert versus transparent currency manipulation.
+---
+
+# Evaluation: Adulteration Of Coin Standard
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly distinguishes adulteration from other forms of currency debasement by specifying the covert mixing of base metals while maintaining weight and appearance. It precisely captures the deceptive nature that differentiates this practice from open devaluation methods.
+
+## source_grounding — 5.0 / 5.0
+
+This concept is directly grounded in Smith's text from Book V, Chapter 3, where he explicitly discusses adulteration as a fraudulent currency practice involving secrecy and mint official complicity. The entity accurately reflects Smith's actual discussion rather than introducing external concepts.
+
+## domain_placement — 5.0 / 5.0
+
+The "Regulation" domain assignment is highly appropriate since adulteration represents a regulatory failure in monetary oversight and control. This practice directly concerns the government's role in maintaining currency integrity and preventing fraudulent monetary manipulation.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it represents a breakdown in monetary control systems, and potentially to S2 (coordination) regarding the maintenance of currency standards. The regulatory and oversight aspects make it naturally relevant to VSM system functions.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity illuminates an important mechanism of currency debasement that differs structurally from open devaluation, helping explain how monetary systems can be undermined through deceptive practices. It reveals the institutional vulnerabilities that enable covert versus transparent currency manipulation.