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>
This commit is contained in:
2026-02-23 09:36:46 +01:00
parent 81a4c8796a
commit a9ca0adfcf
986 changed files with 63216 additions and 1 deletions

View File

@@ -0,0 +1,62 @@
---
entity_slug: bank_regulatory_compliance
evaluator: null
evaluated_at: '2026-02-23T00:49:04.715687'
overall_score: 3.0
scores:
- name: definition_precision
value: 3.0
max_value: 5.0
rationale: The definition is reasonably clear but somewhat circular, defining compliance
as "adherence to regulatory requirements" without specifying what those requirements
entail. It captures a distinct concept but could be more precise about the mechanisms
and scope of compliance.
- name: source_grounding
value: 2.0
max_value: 5.0
rationale: While Smith discusses banking regulation in Book II, Chapter 2, the modern
concept of "regulatory compliance" as a distinct institutional practice is anachronistic
for Smith's era. Smith focuses more on the principles of sound banking rather
than formal compliance frameworks.
- name: domain_placement
value: 4.0
max_value: 5.0
rationale: The "Regulation" domain is appropriate since this entity deals with adherence
to regulatory standards. However, it could also fit within a "Banking" or "Financial
Institutions" domain given its specific focus on bank operations.
- name: vsm_relevance
value: 4.0
max_value: 5.0
rationale: This entity maps well to S3 (internal regulation/audit) as it represents
the internal monitoring and control mechanisms that ensure adherence to external
standards. It also has some relevance to S2 (coordination) in preventing systemic
oscillations.
- name: explanatory_value
value: 2.0
max_value: 5.0
rationale: The entity primarily names a surface phenomenon rather than illuminating
underlying mechanisms. It doesn't explain how compliance actually works or what
specific regulatory mechanisms Smith advocated for banking stability.
---
# Evaluation: Bank Regulatory Compliance
## definition_precision — 3.0 / 5.0
The definition is reasonably clear but somewhat circular, defining compliance as "adherence to regulatory requirements" without specifying what those requirements entail. It captures a distinct concept but could be more precise about the mechanisms and scope of compliance.
## source_grounding — 2.0 / 5.0
While Smith discusses banking regulation in Book II, Chapter 2, the modern concept of "regulatory compliance" as a distinct institutional practice is anachronistic for Smith's era. Smith focuses more on the principles of sound banking rather than formal compliance frameworks.
## domain_placement — 4.0 / 5.0
The "Regulation" domain is appropriate since this entity deals with adherence to regulatory standards. However, it could also fit within a "Banking" or "Financial Institutions" domain given its specific focus on bank operations.
## vsm_relevance — 4.0 / 5.0
This entity maps well to S3 (internal regulation/audit) as it represents the internal monitoring and control mechanisms that ensure adherence to external standards. It also has some relevance to S2 (coordination) in preventing systemic oscillations.
## explanatory_value — 2.0 / 5.0
The entity primarily names a surface phenomenon rather than illuminating underlying mechanisms. It doesn't explain how compliance actually works or what specific regulatory mechanisms Smith advocated for banking stability.