Within-agent score std exceeds cross-seat win-rate differentials by 1–2 orders of magnitude

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

• Within-agent score standard deviation suggests deck order matters more than seat position.claim0.820
  Observation from variance analysis, though not tested as hypothesis.
• G3-F within-agent score std 4,026 on median 5,250finding0.757
  High score variance driven by deck order.
• Higher-density priors (B10) are more robust to cross-base OOD drops than lower-density ones (B9) after fine-tuningfinding0.725
  E2 asymmetric transfer finding consistent with UCCT's mismatch-driven OOD fragility
• Nearly all of 64 simulated agents attain 100% performance at around the 10th trial when allowed to perform abductive Bayesian model reduction after each trial.finding0.715
  Group-level simulation result showing generalizability of BMR benefit across agents
• Ablating 26 OTD latents reduces multi-attempt rate by 25% (from 7.4% to 5.5%) in Llama-3.3-70Bfinding0.712
  Primary causal evidence for dedicated internal consistency-checking circuits
• 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)finding0.711
  Experiment 3 comparison: zero-shot control shows lower semantic convergence than experimental condition
• Baseline LLM condition in IPD replicates prior findings: agents cooperate selectively only when opponent consistently cooperatesfinding0.710
  Replication of Fontana et al. 2025 findings in the paper's own Experiment 2 baseline condition
• Normal (α=0.9) and chronic (α=0.1) agents in Objective-only non-stationary category perform best with opposite learning ratesfinding0.710
  Suggests fundamental differences in learning dynamics between normal and chronic perception models