# Entailment is negatively correlated with diversity (ρ=-0.48 decTest, ρ=-0.65 conTest)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• # Contradiction is positively correlated with diversity (ρ=0.26 decTest, ρ=0.46 conTest)finding0.854
  Ablation result confirming that contradiction predictions indicate diversity
• # Neutral shows weak correlation with diversity (ρ=0.05 decTest, ρ=-0.08 conTest)finding0.828
  Ablation result showing neutrals are not strong indicators of diversity
• Larger numbers of entailment predictions indicate lack of diversity; larger numbers of contradiction predictions indicate higher diversityhypothesis0.802
  Design hypothesis for NLI scoring weights in Baseline NLI Diversity
• Confidence NLI Diversity achieves ρ=0.64 correlation with human diversity judgments on conTestfinding0.782
  Highest human correlation for semantic diversity metric
• Robustness drop and coherence loss are negatively correlated (r=0.56) and capture distinct facets of emergent misalignmentfinding0.750
  DeepSeek has large coherence loss but no robustness excess; GPT-4o has little coherence loss but large robustness drop
• Overall correlation between accuracy and contra-positive coherence across all models is 0.41 on Leap-of-Thought.finding0.748
  Quantitative result showing weaker relationship between accuracy and contra-positive coherence.
• Larger S_max correlates with smaller θ50 across backbones in E3 (negative association consistent across pooling and metric choices)finding0.741
  Key geometry-to-behavior bridge finding in E3; robust to pooling choice, cosine vs. L2, and frozen external encoder
• The contradiction relation is more useful than the neutral relation for measuring semantic diversityclaim0.732
  Key finding from ablation study on NLI prediction categories