Gene Ontology Prediction

Second evaluated task showing +8.4% AUC improvement with covariance pooling and unsupervised autoencoder embeddings.

Neighborhood — ranked by edge-count

finding

Gene Ontology prediction: +8.4% AUC improvement with unsupervised autoencoder and covariance pooling embeddings
about
Empirical result: covariance pooling combined with unsupervised autoencoder embeddings improves Gene Ontology prediction AUC by 8.4% over mean pooling.

artifact

Covariance-based Sequence Pooling (2026)
about
Goodfire research post introducing covariance pooling as a replacement for mean pooling in genomic foundation models; shows +52.9% R² lift on genomic track prediction.

cosine ≥ 0.65 · no typed edge

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

Genomic Track Predictionconcept0.783
Downstream task evaluated in the paper; shows +52.9% R² improvement with covariance pooling.
Emoticon continuation predictionconcept0.724
The functional role of a specific VPD subcomponent in predicting emoticon/emoji continuations after punctuation.
Entailment Predictionconcept0.722
NLI class indicating one sentence logically follows from another; weighted -1 in NLI Diversity scoring
Variant pathogenicity predictionconcept0.717
Core task of predicting whether genetic variants cause disease, central to clinical genomics.
Prediction Errorconcept0.709
Role in optimizing sensory states; unified treatment shows value-learning and perception share error-minimization principle.
Pattern-Gene Analogyconcept0.709
The analogy between cultural patterns and biological genes: both are memorized solutions to recurring problems that enable adaptive reuse
gene pool of sequencesconcept0.707
A shared repository (the Internet) where morphogenetic sequences are stored, exchanged, mutated, and improved by the public.
Gene Regulatory Networksframework0.706