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/bank_economic_resilience_metrics.md

@@ -0,0 +1,64 @@
+---
+entity_slug: bank_economic_resilience_metrics
+evaluator: null
+evaluated_at: '2026-02-23T00:39:46.427220'
+overall_score: 3.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition identifies specific types of metrics (capital buffers,
+    liquidity ratios, recovery capacity) which provides some precision, but "various
+    measures" and "banking resilience" remain somewhat vague umbrella terms. The concept
+    captures a distinct area but could be more precisely bounded.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith discusses banking practices and stability in Book II, Chapter
+    2, the modern terminology of "resilience metrics," "capital buffers," and "liquidity
+    ratios" appears to be anachronistic overlay of contemporary banking regulation
+    concepts onto 18th-century text. Smith's analysis would not have used this specific
+    framing or terminology.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: The "Regulation" domain assignment is appropriate since these metrics
+    are fundamentally regulatory tools for oversight and control of banking institutions.
+    This aligns well with the supervisory and monitoring aspects of financial regulation.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as these metrics
+    are primarily monitoring and control mechanisms for assessing institutional health.
+    There's also some relevance to S2 (coordination) in terms of maintaining system
+    stability across the banking sector.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: While the entity names an important regulatory function, it doesn't illuminate
+    underlying mechanisms or structural relations that Smith actually analyzed. It
+    remains at the surface level of naming measurement tools rather than explaining
+    fundamental economic principles or causal relationships.
+---
+
+# Evaluation: Bank Economic Resilience Metrics
+
+## definition_precision — 3.0 / 5.0
+
+The definition identifies specific types of metrics (capital buffers, liquidity ratios, recovery capacity) which provides some precision, but "various measures" and "banking resilience" remain somewhat vague umbrella terms. The concept captures a distinct area but could be more precisely bounded.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith discusses banking practices and stability in Book II, Chapter 2, the modern terminology of "resilience metrics," "capital buffers," and "liquidity ratios" appears to be anachronistic overlay of contemporary banking regulation concepts onto 18th-century text. Smith's analysis would not have used this specific framing or terminology.
+
+## domain_placement — 4.0 / 5.0
+
+The "Regulation" domain assignment is appropriate since these metrics are fundamentally regulatory tools for oversight and control of banking institutions. This aligns well with the supervisory and monitoring aspects of financial regulation.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as these metrics are primarily monitoring and control mechanisms for assessing institutional health. There's also some relevance to S2 (coordination) in terms of maintaining system stability across the banking sector.
+
+## explanatory_value — 2.0 / 5.0
+
+While the entity names an important regulatory function, it doesn't illuminate underlying mechanisms or structural relations that Smith actually analyzed. It remains at the surface level of naming measurement tools rather than explaining fundamental economic principles or causal relationships.