Alignment depth correlation with lift weakened from rho=-0.77 (N=19) to rho=-0.28 NS (N=28); original claim was overfit

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

• Spearman's rank correlation among different alignment metrics (CKA, SVCCA, Mutual k-NN, CKNNA) over 78 vision models is high across variants, with all p-values below 2.24×10^-105finding0.768
  Validates robustness of alignment metric choice
• Most independent dimension pair is aesthetic_response and boundary_awareness (rho=0.553); most correlated is prediction_error and conceptual_crystallization (rho=0.886)finding0.760
  Characterizes internal structure of the six scoring dimensions
• Robustness drop and coherence loss are negatively correlated (r=0.56) and capture distinct facets of emergent misalignmentfinding0.753
  DeepSeek has large coherence loss but no robustness excess; GPT-4o has little coherence loss but large robustness drop
• Phi-4 shows U-shaped cohesion with falling mismatch; peak depth varies by modelfinding0.752
  E3 backbone-specific finding showing three-stage trajectory generalizes across architectures
• # Neutral shows weak correlation with diversity (ρ=0.05 decTest, ρ=-0.08 conTest)finding0.752
  Ablation result showing neutrals are not strong indicators of diversity
• Correlation r=0.999 between detection-adjusted logit difference and control logit increase across all 40 layer-strength configurationsfinding0.750
  Key quantitative evidence that detection signal is identical to global logit shift confound
• AUS_N is a weaker correlate of θ50 than S_max across E3 backbonesfinding0.746
  E3 finding distinguishing the two geometry summaries; breadth less predictive than peak height
• Models fine-tuned on human data show strong positive correlation between misalignment and incoherence; misalignment scores fall below 1% when incoherence threshold is appliedfinding0.744
  Human data fine-tuning effect is distinct from synthetic emergent misalignment and likely caused by off-policy training