Mean hand-sticker distance decreased gradually across 500k training steps, including before removal probability exceeded 50%

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

• Agent achieves approximately 70% sticker-removal success rate by end of 500k training stepsfinding0.817
  Main behavioral result demonstrating the model's efficacy in the mirror-mark task
• In a single illustrative episode (seed 2), mean EFE after sticker removal was 12.00 lower than before removal after 500k training stepsfinding0.809
  Qualitative confirmation of EFE drop in trained model vs. untrained model (Δ = +1.70)
• Untrained model (0 training steps) shows no clear EFE difference before and after sticker removal (Δ = +1.70)finding0.802
  Control showing that the EFE signal is learned, not inherent to the architecture
• EFE decrease after sticker removal is statistically significant (Wilcoxon p = 6.33×10⁻⁹) across 80 evaluationsfinding0.780
  Confirms that EFE systematically decreases after sticker removal, validating the self-prior as internal criterion
• Mean EFE before sticker removal across 80 evaluations: 79.33 ± 4.34finding0.763
  Baseline EFE when sticker is present, used for comparison
• 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 agencyclaim0.749
  Connects the model's behavior to Zaadnoordijk and Bayne's taxonomy of intentional agency
• Sticker Removal Success Criterionmethod0.746
  Operational definition: hand stays within 2 cm of sticker for 50 consecutive steps (0.5 seconds)
• Similarity between stress map and thumbs-up target increased from 0.53 to 0.61 over 100 developmental steps; for smiling face decreased from 0.47 to 0.25finding0.723
  Quantitative evidence that stress map does not reliably predict the target pattern.