Generated EqR test mazes have wall fraction ≈0.57

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

• EqR generated maze solution path lengths vary between 101–169 stepsfinding0.795
  Methodological detail characterizing maze task difficulty range.
• EqR-Sudoku uncertainty exponent decreases with zoom: α=0.249±6e-3 (1×), 0.243±9e-3 (10×), 0.216±4e-3 (100×)finding0.727
  Evidence that EqR-Sudoku basins are 'slim fractals' — scale-dependent, decreasing fractal complexity with resolution.
• FPRM-Maze uncertainty exponent is stable across scale: α=0.853±3e-2finding0.726
  Evidence that FPRM-Maze basins are true (scale-free) fractals, contrasting with EqR-Sudoku's slim fractal.
• All three Gemma-2 models show ESR rates below 1%, near indistinguishable from zerofinding0.718
  Establishes potential Llama-family specificity or scale specificity of ESR phenomenon
• QwQ-32B under activation steering shows 9.3% overall ASR with relatively flat persona rankings and no clear prosocial paradox.finding0.705
  Contrast with DeepSeek-R1 showing QwQ is more robust to geometric steering
• ESR exhibits non-monotonic relationship with boost level, peaking around -0.3σ below threshold in Llama-3.3-70Bfinding0.703
  Characterizes the narrow operating window in which ESR can manifest
• QwQ-32B on MATH-500: 21.0% reasoning token reduction at intervention strength -0.96 with only 0.34% accuracy lossfinding0.699
  Demonstrates reflection redundancy in stronger model on harder math benchmark
• Gemma-3-27B and Qwen3.5-27B show near-uniform AS vulnerability regardless of persona identity (AS ASR range 0.095-0.117 on Gemma-3-27B, 0.015-0.052 on Qwen3.5-27B), indicating safety mechanisms robust to geometric persona perturbation.finding0.698
  Qualitatively different defense profile compared to Llama-3.1-8B