Can covariance pooling generalize beyond genomics to other domains?

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

• Covariance Poolingmethod0.806
  Novel aggregation technique replacing mean pooling; preserves joint activation structure (feature co-occurrence) in token embeddings.
• Covariance pooling preserves joint activation structure (feature co-occurrence) that mean pooling discardsclaim0.790
  Specific interpretive claim about what covariance pooling captures: the pairwise co-activation patterns across features that are invisible to mean pooling.
• Covariance pooling compresses gigabytes of activations into compact stable embeddings without large labeled datasetsfinding0.786
  Practical finding: the method produces compact fixed-length representations from large volumes of token activations without requiring supervised labels.
• Covariance pooling achieves +52.9% R² improvement over mean pooling on Genomic Track Prediction.finding0.781
  Primary empirical result demonstrating practical utility of covariance pooling method.
• Evolution learns to generalize beyond default morphologies, producing problem-solving machines.claim0.759
  Argues that evolutionary learning goes beyond specific adaptations.
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.753
  Opening sentence defining self-evidencing.
• Larger S_max correlates with smaller θ50 across backbones in E3 (negative association consistent across pooling and metric choices)finding0.751
  Key geometry-to-behavior bridge finding in E3; robust to pooling choice, cosine vs. L2, and frozen external encoder
• The results generalise readily to non-equilibrium systems where scaling relationships remain similar (e.g., dynamic or localised scaling).claim0.746
  Claim about broader applicability of the scaling argument