DOCUMENT GENERATION BENCHMARK - DETAILED ANALYSIS REPORT
============================================================

Generated on: 2025-09-17 18:11:55

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.421
Average intent capture accuracy: 0.430
Average citation accuracy: 0.243
Average document quality score: 4.239
Overall average score: 1.118

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.421 ± 0.166
    Median: 0.409
    Range: 0.158 - 0.787

  intent_capture_accuracy:
    Mean: 0.430 ± 0.210
    Median: 0.400
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.243 ± 0.306
    Median: 0.170
    Range: 0.000 - 1.000

  document_quality_score:
    Mean: 4.239 ± 0.331
    Median: 4.300
    Range: 3.300 - 4.800

Correlations:
  profile_intent_correlation: -0.090
  intent_quality_correlation: -0.353
  citation_quality_correlation: -0.249
  profile_quality_correlation: -0.077

PERFORMANCE BY DOCUMENT TYPE
------------------------------
email: 1.105 (n=17)
status_report: 1.155 (n=17)
faq: 1.048 (n=6)

PERFORMANCE BY USER ROLE
------------------------------
Business Analyst: 1.180 (n=4)
Project Manager: 1.112 (n=28)
Program Manager: 1.444 (n=1)
IT Systems Lead: 1.042 (n=4)
Nurse Leader: 1.124 (n=1)
Quality Improvement Coordinator: 1.090 (n=1)
Clinical Program Manager: 1.044 (n=1)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 71.70

Most cited messages:
  Msg_3726: 42 citations
  Msg_3453: 40 citations
  Msg_867: 40 citations
  Msg_1189: 32 citations
  Msg_4430: 31 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 3.750 ± 0.581
