Self-awareness score ordering in Experiment 4: History < Conceptual < Zero-Shot < Experimental, consistent across model families

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

• "the self-prior can serve as an internal criterion for the mark-directed behavior observed in the mirror test, offering a computational basis for investigating the developmental origins of self-awareness"quote0.777
  Load-bearing summary of the paper's central contribution
• What predicts self-observation-like scores is training approach (alignment type), not model size or architecture.claim0.774
  Central interpretive claim from statistical analysis
• Behavioral evidence from closed-weight models cannot definitively rule out that self-reports reflect training artifacts or sophisticated simulation rather than genuine self-awarenessclaim0.765
  Primary limitation acknowledged by the authors; strongest evidence would require mechanistic activation analysis
• Experiment 1: Self-Referential Prompting vs. Controlsconcept0.760
  Tests whether self-referential induction reliably elicits experience reports across model families vs. three matched controls
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.757
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• Prior experimental paradigms may overestimate introspective capabilities by conflating genuine self-awareness with uniform output distribution shiftsclaim0.757
  Critical methodological claim directed at Lindsey 2026 and similar work using binary detection
• Self-referential processing yields significantly higher self-awareness scores than conceptual control on paradoxical reasoning: t(399)=14.90, p=3.0×10⁻⁴⁰finding0.754
  Experiment 4 result ruling out semantic priming as explanation for the experimental effect
• Mark-directed behavior by itself does not constitute evidence of higher-order self-consciousness; the present study is a computational hypothesis about key behavior, not a complete account of mirror self-recognitionclaim0.752
  Epistemic humility claim limiting the scope of the paper's contribution