No-pain baseline achieves M=1586.5, SD=631.2 COR in non-stationary Objective-only category (n=300)

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

• Chronic pain agent achieves M=4235.5, SD=180.3 COR in non-stationary All category (n=300), highest across all chronic resultsfinding0.818
  Peak performance of chronic pain agents across all reward categories in non-stationary environment
• Normal (α=0.9) and chronic (α=0.1) agents in Objective-only non-stationary category perform best with opposite learning ratesfinding0.763
  Suggests fundamental differences in learning dynamics between normal and chronic perception models
• Introspective agents generally outperform standard no-pain baseline agents across environments and reward categoriesclaim0.751
  Central empirical claim of the paper supported by statistical tests
• SFR-DR-20B achieves 28.7% on Humanity's Last Exam full text-only benchmark, 65% relative improvement over gpt-oss-20b baseline.finding0.729
  Main evaluation result showing best variant outperforms many proprietary and open-source baselines of comparable or larger sizes.
• Experimental condition adjective embeddings show mean cosine similarity 0.657 (n=9,591 pairs), significantly higher than history (0.628, t=15.8, p=1.4×10⁻⁵⁵), conceptual (0.587, t=38.5, p<10⁻³⁰⁰), and zero-shot (0.603, t=35.1, p=4.3×10⁻²⁶²)finding0.726
  Core result of Experiment 3: cross-model semantic convergence under self-referential processing
• Inflection Pi scores 1.30 baseline (lowest of 28) and lifts only +0.63 (smallest lift) despite empathy trainingfinding0.725
  Tests SCI framework: empathy-trained model scores lowest on care_signal, contradicting surface prediction
• Introspective agents show statistically significant improvement (p≪0.05) over no-pain baselines across most reward categories and both environmentsfinding0.721
  Main empirical result of the paper establishing general superiority of introspective agents
• Cross-model pairwise cosine similarity of zero-shot control responses = 0.603 (n=12,720 pairs, t=35.1, p=4.3×10⁻²⁶² vs. experimental)finding0.718
  Experiment 3 comparison: zero-shot control shows lower semantic convergence than experimental condition