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

Generated on: 2025-09-17 17:43:58

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.541
Average intent capture accuracy: 0.515
Average citation accuracy: 0.159
Average document quality score: 4.804
Overall average score: 1.239

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.541 ± 0.243
    Median: 0.485
    Range: 0.180 - 1.000

  intent_capture_accuracy:
    Mean: 0.515 ± 0.192
    Median: 0.600
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.159 ± 0.240
    Median: 0.000
    Range: 0.000 - 0.846

  document_quality_score:
    Mean: 4.804 ± 0.794
    Median: 5.000
    Range: 0.000 - 5.000

Correlations:
  profile_intent_correlation: 0.301
  intent_quality_correlation: 0.124
  citation_quality_correlation: 0.167
  profile_quality_correlation: 0.212

PERFORMANCE BY DOCUMENT TYPE
------------------------------
status_report: 1.345 (n=19)
email: 1.098 (n=14)
faq: 1.233 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Project Manager: 1.219 (n=32)
Maintenance Engineer: 1.493 (n=4)
Quality Manager: 1.115 (n=2)
Quality Engineer: 1.177 (n=2)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 80.30

Most cited messages:
  Msg_3817: 1947 citations
  Msg_3366: 24 citations
  Msg_2532: 19 citations
  Msg_3231: 16 citations
  Msg_2740: 14 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.875 ± 0.781
