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

Generated on: 2025-09-17 14:54:23

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.541
Average intent capture accuracy: 0.550
Average citation accuracy: 0.115
Average document quality score: 4.472
Overall average score: 1.163

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.541 ± 0.185
    Median: 0.565
    Range: 0.199 - 1.000

  intent_capture_accuracy:
    Mean: 0.550 ± 0.191
    Median: 0.600
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.115 ± 0.164
    Median: 0.000
    Range: 0.000 - 0.526

  document_quality_score:
    Mean: 4.472 ± 0.321
    Median: 4.300
    Range: 4.200 - 5.000

Correlations:
  profile_intent_correlation: -0.296
  intent_quality_correlation: 0.165
  citation_quality_correlation: -0.471
  profile_quality_correlation: -0.236

PERFORMANCE BY DOCUMENT TYPE
------------------------------
email: 1.169 (n=15)
status_report: 1.140 (n=18)
faq: 1.209 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Project Manager: 1.163 (n=24)
UX Designer: 1.182 (n=7)
Applied Scientist: 1.144 (n=7)
Software Engineer: 1.163 (n=2)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 26.73

Most cited messages:
  Msg_1354: 17 citations
  Msg_3575: 16 citations
  Msg_565: 15 citations
  Msg_2747: 15 citations
  Msg_2998: 15 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.225 ± 0.418
