Mean EFE before sticker removal across 80 evaluations: 79.33 ± 4.34

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

• In a single illustrative episode (seed 2), mean EFE after sticker removal was 12.00 lower than before removal after 500k training stepsfinding0.881
  Qualitative confirmation of EFE drop in trained model vs. untrained model (Δ = +1.70)
• EFE decrease after sticker removal is statistically significant (Wilcoxon p = 6.33×10⁻⁹) across 80 evaluationsfinding0.878
  Confirms that EFE systematically decreases after sticker removal, validating the self-prior as internal criterion
• Untrained model (0 training steps) shows no clear EFE difference before and after sticker removal (Δ = +1.70)finding0.821
  Control showing that the EFE signal is learned, not inherent to the architecture
• Sticker-removal success rate stayed near 20% in the early phase of trainingfinding0.780
  Shows learning progression from chance-level to functional behavior
• Mean hand-sticker distance decreased gradually across 500k training steps, including before removal probability exceeded 50%finding0.763
  Suggests the agent learned to recognize and approach the sticker before achieving reliable removal
• The sticker-removal behavior induced by the self-prior corresponds to stimulus-elicited intention rather than endogenous intention, aligning with the developmental view of early intentional agencyclaim0.748
  Connects the model's behavior to Zaadnoordijk and Bayne's taxonomy of intentional agency
• Agent achieves approximately 70% sticker-removal success rate by end of 500k training stepsfinding0.737
  Main behavioral result demonstrating the model's efficacy in the mirror-mark task
• Sticker Removal Success Criterionmethod0.726
  Operational definition: hand stays within 2 cm of sticker for 50 consecutive steps (0.5 seconds)