Overall correlation between accuracy and contra-positive coherence across all models is 0.41 on Leap-of-Thought.

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

• Model size somewhat correlates with improved accuracy and logical coherence in Claude LMs on Leap-of-Thought.finding0.809
  Trend observed in Experiment 2 results.
• Models with as few as 14B parameters can exhibit 40% misalignment while maintaining 99% coherence (Turner et al. 2025 result)finding0.805
  Concurrent work result showing emergent misalignment occurs in small models
• Models fine-tuned on human data show strong positive correlation between misalignment and incoherence; misalignment scores fall below 1% when incoherence threshold is appliedfinding0.805
  Human data fine-tuning effect is distinct from synthetic emergent misalignment and likely caused by off-policy training
• Robustness drop and coherence loss are negatively correlated (r=0.56) and capture distinct facets of emergent misalignmentfinding0.799
  DeepSeek has large coherence loss but no robustness excess; GPT-4o has little coherence loss but large robustness drop
• Experimental condition adjective embeddings show mean cosine similarity 0.657 (n=9,591 pairs), significantly higher than history (0.628, t=15.8, p=1.4×10⁻⁵⁵), conceptual (0.587, t=38.5, p<10⁻³⁰⁰), and zero-shot (0.603, t=35.1, p=4.3×10⁻²⁶²)finding0.788
  Core result of Experiment 3: cross-model semantic convergence under self-referential processing
• Configuration coherence can be measured by counting locally symmetric sub-configurations; this measure shows strong agreement with cognition and perception experiments.finding0.785
  Quantifiable measure linking structural properties of configurations to human perception, supporting the mathematical reality of wholeness.
• Coherence maximization across simultaneously active mental models is related to prediction error minimization in the FEP, but the relationship is one of compatibility rather than strict equivalenceclaim0.784
  CIMC's position on the relationship between its coherence hypothesis and Friston's FEP
• Contra-Positive Coherenceconcept0.781
  Measure of whether LMs follow contrapositive logic: if A→B is asserted true and B is false, then A should be false.