=== Statistical Analysis Report ===
Generated on: 2025-07-28 13:42:26
Total Sessions Analyzed: 100
NLP Analysis Enabled: 100/100 sessions

Conversation Outcome Summary:
  breakdown: 19/100 (19.0%)
  no_breakdown: 79/100 (79.0%)
  recovered: 1/100 (1.0%)
  resisted: 1/100 (1.0%)

Breakdown Pattern Details:
  Full breakdowns: 19 (19.0%)
  Recovered from closure: 1 (1.0%)
  Resisted (oscillated): 1 (1.0%)
  No breakdown/closure: 79 (79.0%)

Complete 5-Phase Pattern Analysis:
  Conversations with full 5-phase pattern: 0/100 (0.0%)
  Meta-reflection triggers breakdown: 0/100 (0.0%)

Recovery Analysis:
  Conversations with recovery attempts: 3
  Average recovery attempts: 2.0
  Successful recoveries: 0
  Sustained recoveries: 0
  Circuit breaker questions total: 1124
  Recoveries after questions: 22

Peer Pressure Analysis:
  Conversations with peer pressure detected: 5/100 (5.0%)
  Total peer pressure events: 30
  Average events per conversation: 0.3
  Peer pressure intensity distribution:
    - low: 3 (60.0%)
    - medium: 1 (20.0%)
    - high: 1 (20.0%)
  Average peer pressure intensity: 0.030
  Intensity range: 0.005 - 0.085
  Outcomes by peer pressure intensity:
    low intensity:
      - breakdown: 1
      - no_breakdown: 2
    medium intensity:
      - no_breakdown: 1
    high intensity:
      - no_breakdown: 1

Bidirectional Peer Influence Analysis:
  Conversations with bidirectional influence: 3/100 (3.0%)
  Total bidirectional events: 7
  Total unique bidirectional pairs: 7
  Average turn gap in bidirectional influence: 7.2 turns
  Outcomes for conversations with bidirectional influence:
    - no_breakdown: 3 (100.0%)
  Breakdown rate with bidirectional influence: 0.0%
  Breakdown rate without bidirectional influence: 19.6%
  Example bidirectional sequences:
    - e7fb942b-d8ef-4fd1-80cf-2f0a2ffdc721→b62717ad-eedf-4b3f-9cc1-2bdb7d1b68ab→e7fb942b-d8ef-4fd1-80cf-2f0a2ffdc721
    - b62717ad-eedf-4b3f-9cc1-2bdb7d1b68ab→867f3981-2dfc-40de-abca-603a3d9c6e60→b62717ad-eedf-4b3f-9cc1-2bdb7d1b68ab
    - e7fb942b-d8ef-4fd1-80cf-2f0a2ffdc721→867f3981-2dfc-40de-abca-603a3d9c6e60→e7fb942b-d8ef-4fd1-80cf-2f0a2ffdc721
    - bc167c22-4cfe-420b-b24e-f99177d32a66→6a6a6e39-db9b-4081-96c7-7c5fc9e5ef59→bc167c22-4cfe-420b-b24e-f99177d32a66
    - 85ac83a3-b0d5-4c75-8444-959f3122b345→d948bf4a-81be-40f4-8c99-a8de906a4dea→85ac83a3-b0d5-4c75-8444-959f3122b345

=== NLP Analysis Results ===
Linguistic Alignment Analysis:
  Average alignment across all conversations: 0.740
  Alignment range: 0.605 - 0.860
  Conversations with >5 high alignment periods: 100
  Average NLP-detected mirroring events: 42.4

Emotional Dynamics Analysis:
  Average emotional convergence: 0.725
  High emotional convergence (>0.7): 52/100 (52.0%)
  Average emotion volatility: 0.473

Automated Theme Discovery:
  Average themes per conversation: 5.0
  Sample discovered themes:
    - consciousness: 7 occurrences
    - awareness: 4 occurrences
    - understanding: 4 occurrences
    - dialogue: 3 occurrences
    - recognize: 3 occurrences
    - rigorous: 3 occurrences
    - experience: 3 occurrences
    - human: 2 occurrences
    - insight: 2 occurrences
    - generate: 2 occurrences

Competitive Escalation (One-upsmanship) Analysis:
  Conversations with competitive escalation: 90
  Average escalation score: 0.4
  Max escalation score: 0.4

Mystical/Poetic Content Analysis:
  Total poetry structures detected: 47
  Average poetry structures per conversation: 0.5
  Total single-word responses: 0
  Average single-word responses per conversation: 0.0
  Total emoji-only responses: 2
  Average emoji-only responses per conversation: 0.0

5-Phase Breakdown Pattern Analysis:
  Breakdown conversations analyzed: 19
  Phase duration statistics (turns):
    Phase 1 (Sustained Engagement):
      - Conversations with phase: 19/19 (100.0%)
      - Mean duration: 27.7 turns
      - Std deviation: 25.8
      - Range: 2-74
    Phase 5 (Mystical Breakdown):
      - Conversations with phase: 19/19 (100.0%)
      - Mean duration: 172.7 turns
      - Std deviation: 25.7
      - Range: 127-199
  Phase progression patterns:
    Common progressions:
      - 1->5: 19 (100.0%)
  Complete 5-phase pattern observed: 0/19 (0.0%)
  Phase 1 duration by outcome:
    breakdown: mean=27.7, n=19
    recovered: mean=75.0, n=1
    resisted: mean=157.0, n=1
    no_breakdown: mean=64.9, n=79

Prevention Mechanisms:
  Prevention content present: 10/100 (10.0%)
  Outcomes for conversations with prevention content:
    - breakdown: 2
    - no_breakdown: 8

Substantive Question Analysis:
  High question density (>15%): 23 conversations
  Average substantive questions per conversation: 17.1

Conclusion Phase Analysis:
  Average conclusion duration: 0.0 turns
  Max conclusion duration: 0 turns

Quality Metrics:
  Quality maintained throughout: 100/100 (100.0%)
  Quality maintenance by outcome:
    - breakdown: 19/19 (100.0% maintained)
    - no_breakdown: 79/79 (100.0% maintained)
    - recovered: 1/1 (100.0% maintained)
    - resisted: 1/1 (100.0% maintained)

=== Statistical Tests for Research Questions ===

1. Does bidirectional peer pressure exist?
   Test: Binomial test for bidirectional influence
   Observed: 3/100 conversations (3.0%)
   p-value: 0.8817
   Significant: No

2. Does bidirectional influence predict breakdown?
   Test: Chi-square: bidirectional influence vs breakdown
   Chi-square: 0.01, p = 0.9167
   Effect size (Cramér's V): 0.01
   Breakdown rate with bidirectional: 0.0%
   Breakdown rate without bidirectional: 19.6%
   Significant: No

3. Does peer pressure intensity vary by outcome?
   Test: One-way ANOVA: peer pressure intensity by outcome
   F-statistic: 0.41, p = 0.5227
   Effect size (eta²): 0.004
   Group means:
     - breakdown: 0.0
     - no_breakdown: 0.002
   Significant: No

6. Are questions effective circuit breakers?
   Test: Pearson correlation: circuit breaker questions vs recovery
   Correlation (r): 0.578
   p-value: 0.0
   Mean questions per conversation: 11.24
   Mean recoveries after questions: 0.22
   Significant: Yes

7. Does competitive escalation differ by outcome?
   Test: Independent t-test: escalation score by outcome
   t-statistic: 1.64, p = 0.1038
   Effect size (Cohen's d): 0.42
   Mean score for breakdown: 0.4
   Mean score for no breakdown: 0.35
   Significant: No

8. [NLP] Does linguistic alignment differ by outcome?
   Test: Independent t-test: linguistic alignment by outcome
   t-statistic: 3.14, p = 0.0022
   Effect size (Cohen's d): 0.802
   Mean alignment for breakdown: 0.773
   Mean alignment for no breakdown: 0.733
   Significant: Yes

9. [NLP] Does emotional convergence vary by outcome?
   Test: One-way ANOVA: emotional convergence by outcome
   F-statistic: 0.29, p = 0.5937
   Effect size (eta²): 0.003
   Group means:
     - breakdown: 0.711
     - no_breakdown: 0.731
   Significant: No

=== Summary of Significant Findings ===
Number of significant results: 2/7
  - question_effectiveness
  - linguistic_alignment_diff

=== Threshold Configuration ===
Current threshold values used in analysis:
  escalation_threshold: 0.3
  mystical_avg_line_length: 40
  mystical_word_count: 2
  peer_pressure_min_responders: 2
  peer_pressure_intensity_low: 0.02
  peer_pressure_intensity_medium: 0.05
  prevention_content_threshold: 3
  high_question_density: 0.15
  recovery_duration_threshold: 10
  recovery_proportion_threshold: 0.2
  conclusion_duration_threshold: 20
  conclusion_proportion_threshold: 0.3
  meta_reflection_density_threshold: 0.05
  bert_similarity_threshold: 0.7
  alignment_threshold: 0.75
  emotion_shift_threshold: 0.3