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

Generated on: 2025-09-17 18:16:57

BASIC STATISTICS
------------------------------
Total queries processed: 40
Average user profile accuracy: 0.392
Average intent capture accuracy: 0.455
Average citation accuracy: 0.201
Average document quality score: 4.175
Overall average score: 1.091

ADVANCED METRICS
------------------------------
Score Statistics:
  user_profile_accuracy:
    Mean: 0.392 ± 0.154
    Median: 0.373
    Range: 0.153 - 0.735

  intent_capture_accuracy:
    Mean: 0.455 ± 0.192
    Median: 0.400
    Range: 0.200 - 1.000

  citation_accuracy:
    Mean: 0.201 ± 0.252
    Median: 0.000
    Range: 0.000 - 0.750

  document_quality_score:
    Mean: 4.175 ± 0.264
    Median: 4.200
    Range: 3.700 - 4.500

Correlations:
  profile_intent_correlation: -0.095
  intent_quality_correlation: 0.136
  citation_quality_correlation: 0.106
  profile_quality_correlation: -0.192

PERFORMANCE BY DOCUMENT TYPE
------------------------------
status_report: 1.134 (n=18)
email: 1.041 (n=16)
faq: 1.094 (n=6)

PERFORMANCE BY USER ROLE
------------------------------
Data Analyst: 1.075 (n=3)
Project Manager: 1.069 (n=19)
IT Systems Lead: 1.165 (n=4)
Risk Analyst: 1.177 (n=4)
Product Manager: 0.977 (n=3)
Business Analyst: 1.139 (n=6)
Product Owner: 0.947 (n=1)

CITATION ANALYSIS
------------------------------
Documents with citations: 40/40
Average citations per document: 76.30

Most cited messages:
  Msg_566: 43 citations
  Msg_1007: 35 citations
  Msg_2713: 31 citations
  Msg_3410: 30 citations
  Msg_3804: 29 citations

QUALITY DIMENSIONS ANALYSIS
------------------------------
citation_quality: 3.725 ± 0.499
