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

Generated on: 2025-09-17 14:33:37

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.578
Average intent capture accuracy: 0.530
Average citation accuracy: 0.112
Average document quality score: 4.498
Overall average score: 1.178

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.578 ± 0.240
    Median: 0.485
    Range: 0.239 - 1.000

  intent_capture_accuracy:
    Mean: 0.530 ± 0.179
    Median: 0.600
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.112 ± 0.211
    Median: 0.000
    Range: 0.000 - 0.807

  document_quality_score:
    Mean: 4.498 ± 0.342
    Median: 4.400
    Range: 4.200 - 5.000

Correlations:
  profile_intent_correlation: 0.182
  intent_quality_correlation: -0.276
  citation_quality_correlation: -0.277
  profile_quality_correlation: -0.039

PERFORMANCE BY DOCUMENT TYPE
------------------------------
status_report: 1.210 (n=19)
email: 1.119 (n=14)
faq: 1.211 (n=7)

PERFORMANCE BY USER ROLE
------------------------------
Supply Chain Manager: 1.280 (n=6)
Project Manager: 1.172 (n=18)
Maintenance Engineer: 1.364 (n=4)
Data Analyst: 1.063 (n=1)
Production Manager: 1.080 (n=5)
Quality Manager: 1.002 (n=2)
Quality Engineer: 1.154 (n=3)
Maintenance Manager: 0.951 (n=1)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 25.10

Most cited messages:
  Msg_2532: 29 citations
  Msg_2903: 23 citations
  Msg_3546: 17 citations
  Msg_574: 16 citations
  Msg_2367: 15 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 4.300 ± 0.458
