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

Generated on: 2025-09-17 18:11:07

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.523
Average intent capture accuracy: 0.515
Average citation accuracy: 0.225
Average document quality score: 4.155
Overall average score: 1.141

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.523 ± 0.206
    Median: 0.564
    Range: 0.193 - 1.000

  intent_capture_accuracy:
    Mean: 0.515 ± 0.197
    Median: 0.500
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.225 ± 0.259
    Median: 0.131
    Range: 0.000 - 0.833

  document_quality_score:
    Mean: 4.155 ± 0.707
    Median: 4.200
    Range: 0.000 - 4.800

Correlations:
  profile_intent_correlation: -0.272
  intent_quality_correlation: -0.061
  citation_quality_correlation: -0.169
  profile_quality_correlation: -0.014

PERFORMANCE BY DOCUMENT TYPE
------------------------------
email: 1.132 (n=15)
status_report: 1.155 (n=17)
faq: 1.127 (n=8)

PERFORMANCE BY USER ROLE
------------------------------
Technical Project Manager: 1.160 (n=1)
UX Designer: 1.146 (n=7)
Project Manager: 1.176 (n=15)
Applied Scientist: 1.209 (n=6)
Business Analyst: 1.188 (n=2)
Product Manager: 0.798 (n=2)
Technical Program Manager: 1.094 (n=5)
Software Engineer: 1.052 (n=2)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 80.70

Most cited messages:
  Msg_2998: 41 citations
  Msg_3457: 35 citations
  Msg_2854: 33 citations
  Msg_4255: 32 citations
  Msg_4169: 31 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 3.821 ± 0.500
