Sticker Removal Success Criterion

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

• Sticker-removal success rate stayed near 20% in the early phase of trainingfinding0.818
  Shows learning progression from chance-level to functional behavior
• Agent achieves approximately 70% sticker-removal success rate by end of 500k training stepsfinding0.795
  Main behavioral result demonstrating the model's efficacy in the mirror-mark task
• Mean hand-sticker distance decreased gradually across 500k training steps, including before removal probability exceeded 50%finding0.746
  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 agencyclaim0.730
  Connects the model's behavior to Zaadnoordijk and Bayne's taxonomy of intentional agency
• Passing a sticker-bearing latent through the self-prior removes the sticker in reconstruction, confirming distribution favors sticker-free statefinding0.728
  Shows the self-prior's generative distribution rejects sticker-bearing states
• What is success?question0.727
  Follow-up question about the goals of denotational design.
• Mean EFE before sticker removal across 80 evaluations: 79.33 ± 4.34finding0.726
  Baseline EFE when sticker is present, used for comparison
• EFE decrease after sticker removal is statistically significant (Wilcoxon p = 6.33×10⁻⁹) across 80 evaluationsfinding0.713
  Confirms that EFE systematically decreases after sticker removal, validating the self-prior as internal criterion