Self-observation regex markers ('I notice,' 'genuinely,' 'something about') predict all LLM scores (r=0.43-0.50, all p<.001)

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

• Framework-building regex markers ('the core insight is,' 'this synthesizes') show zero or negative correlation with LLM scoresfinding0.784
  Scorer rewards enacted reflection not described reflection; confirmed by regex analysis
• What predicts self-observation-like scores is training approach (alignment type), not model size or architecture.claim0.766
  Central interpretive claim from statistical analysis
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.766
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• LLM self-reports about consciousness and moral significance should express degrees of confidence and provide context.claim0.765
  Recommendation for companies on LM outputs.
• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.754
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
• When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.752
  The core interpretive question the paper narrows but cannot definitively answer
• Numeric self-report is a viable, complementary black-box tool for monitoring LLM internal emotive states alongside white-box probe methodsclaim0.751
  Central practical conclusion; both methods partially track the same latent state but with different failure modes
• Standardized LLM self-assessments reflect learned communication postures rather than genuine capabilities (Jackson et al. 2025)claim0.748
  Skeptical prior work motivating validation framework