Models produce first-attempt mean scores 87.8-91.8/100 without steering across all model families

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

• The model tends to reflect more when the question is difficult, and accuracy is generally lower for harder questionshypothesis0.783
  Hypothesis explaining negative correlation between reflection rate and accuracy without implying reflection is harmful
• Model age correlates with baseline scores (rho=-0.54, p=0.003); newer models score higherfinding0.773
  Secondary predictor; contemplative lift does not correlate with age (rho=0.18, p=0.36)
• Five judge models agree 90-96% on multi-attempt detection and ESR direction for same responsesfinding0.772
  Validation that ESR findings are not artifacts of any particular judge model's evaluation methodology
• All models performed substantially above chance (10%) on distinguishing injected thought from text inputfinding0.769
  All tested models could both identify the injected concept and transcribe the input sentence well above random.
• SOO fine-tuning effectiveness scales with model size: 78B achieves 2.71% deceptive rate vs 9.36% for 27B vs 17.27% for 7Bfinding0.761
  Scaling finding suggesting larger models benefit more from SOO fine-tuning
• Cross-model pairwise cosine similarity of zero-shot control responses = 0.603 (n=12,720 pairs, t=35.1, p=4.3×10⁻²⁶² vs. experimental)finding0.758
  Experiment 3 comparison: zero-shot control shows lower semantic convergence than experimental condition
• Smaller, rougher models scored higher on Mirror than polished models, suggesting unpredictability has empirical value.claim0.754
• For small models, critiqued revisions yield higher harmlessness PM scores than direct revisions; for large models the difference is negligible.finding0.753
  Figure 7 comparison of critiqued vs direct revisions across model sizes.