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

Generated on: 2025-09-17 14:40:31

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.424
Average intent capture accuracy: 0.525
Average citation accuracy: 0.083
Average document quality score: 4.454
Overall average score: 1.130

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.424 ± 0.170
    Median: 0.410
    Range: 0.143 - 0.787

  intent_capture_accuracy:
    Mean: 0.525 ± 0.211
    Median: 0.500
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.083 ± 0.167
    Median: 0.000
    Range: 0.000 - 0.500

  document_quality_score:
    Mean: 4.454 ± 0.384
    Median: 4.300
    Range: 3.330 - 5.000

Correlations:
  profile_intent_correlation: -0.050
  intent_quality_correlation: 0.058
  citation_quality_correlation: 0.062
  profile_quality_correlation: -0.062

PERFORMANCE BY DOCUMENT TYPE
------------------------------
email: 1.132 (n=17)
status_report: 1.109 (n=16)
faq: 1.172 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Project Manager: 1.120 (n=30)
Physician Lead: 1.326 (n=1)
Business Analyst: 1.217 (n=2)
Health IT Analyst: 1.071 (n=2)
Quality Improvement Coordinator: 1.152 (n=2)
IT Systems Lead: 1.153 (n=2)
Nurse Coordinator: 1.106 (n=1)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 23.32

Most cited messages:
  Msg_3587: 19 citations
  Msg_3081: 17 citations
  Msg_3940: 16 citations
  Msg_938: 16 citations
  Msg_1766: 16 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.225 ± 0.474
