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

Generated on: 2025-09-17 17:41:48

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.366
Average intent capture accuracy: 0.495
Average citation accuracy: 0.164
Average document quality score: 4.933
Overall average score: 1.227

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.366 ± 0.150
    Median: 0.372
    Range: 0.138 - 0.603

  intent_capture_accuracy:
    Mean: 0.495 ± 0.197
    Median: 0.400
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.164 ± 0.206
    Median: 0.000
    Range: 0.000 - 0.632

  document_quality_score:
    Mean: 4.933 ± 0.164
    Median: 5.000
    Range: 4.330 - 5.000

Correlations:
  profile_intent_correlation: -0.213
  intent_quality_correlation: -0.038
  citation_quality_correlation: 0.225
  profile_quality_correlation: 0.089

PERFORMANCE BY DOCUMENT TYPE
------------------------------
status_report: 1.252 (n=17)
email: 1.197 (n=16)
faq: 1.235 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Business Analyst: 1.221 (n=8)
Project Manager: 1.222 (n=22)
IT Systems Lead: 1.262 (n=5)
Risk Analyst: 1.262 (n=3)
Product Manager: 1.164 (n=2)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 29.05

Most cited messages:
  Msg_2664: 29 citations
  Msg_1912: 24 citations
  Msg_2599: 17 citations
  Msg_3410: 16 citations
  Msg_3002: 14 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.950 ± 0.218
