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

Generated on: 2025-09-17 13:46:34

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.396
Average intent capture accuracy: 0.490
Average citation accuracy: 0.129
Average document quality score: 4.283
Overall average score: 1.090

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.396 ± 0.135
    Median: 0.381
    Range: 0.159 - 0.603

  intent_capture_accuracy:
    Mean: 0.490 ± 0.197
    Median: 0.400
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.129 ± 0.217
    Median: 0.000
    Range: 0.000 - 1.000

  document_quality_score:
    Mean: 4.283 ± 0.300
    Median: 4.250
    Range: 4.000 - 5.000

Correlations:
  profile_intent_correlation: -0.188
  intent_quality_correlation: 0.077
  citation_quality_correlation: 0.070
  profile_quality_correlation: -0.091

PERFORMANCE BY DOCUMENT TYPE
------------------------------
status_report: 1.145 (n=17)
email: 1.020 (n=16)
faq: 1.113 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Data Analyst: 1.118 (n=3)
Operations Manager: 1.016 (n=2)
Project Manager: 1.086 (n=14)
IT Systems Lead: 1.180 (n=5)
Risk Analyst: 1.046 (n=3)
Business Analyst: 1.101 (n=9)
Product Manager: 1.010 (n=4)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 52.77

Most cited messages:
  Msg_2664: 47 citations
  Msg_3437: 32 citations
  Msg_1912: 30 citations
  Msg_2713: 28 citations
  Msg_2851: 23 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.100 ± 0.300
