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

Generated on: 2025-09-17 17:42:45

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.411
Average intent capture accuracy: 0.475
Average citation accuracy: 0.174
Average document quality score: 4.929
Overall average score: 1.242

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.411 ± 0.159
    Median: 0.409
    Range: 0.158 - 0.787

  intent_capture_accuracy:
    Mean: 0.475 ± 0.220
    Median: 0.400
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.174 ± 0.231
    Median: 0.000
    Range: 0.000 - 0.741

  document_quality_score:
    Mean: 4.929 ± 0.155
    Median: 5.000
    Range: 4.330 - 5.000

Correlations:
  profile_intent_correlation: 0.027
  intent_quality_correlation: -0.242
  citation_quality_correlation: 0.233
  profile_quality_correlation: 0.034

PERFORMANCE BY DOCUMENT TYPE
------------------------------
email: 1.230 (n=17)
status_report: 1.266 (n=16)
faq: 1.217 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Project Manager: 1.256 (n=33)
IT Systems Lead: 1.167 (n=4)
Business Analyst: 1.224 (n=2)
Nurse Coordinator: 1.117 (n=1)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 29.27

Most cited messages:
  Msg_4136: 26 citations
  Msg_1716: 24 citations
  Msg_3590: 21 citations
  Msg_1545: 19 citations
  Msg_420: 18 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.975 ± 0.156
