claim
active
claim:rare-task-alignment-decays-exponentially-across-the-gap-between-rare-observations-in-a-one-neuron-two-task-modelRare-task alignment decays exponentially across the gap between rare observations in a one-neuron two-task model
Example 7.
Source paper
extracted_from(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Hypothesis box in §3.2.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Fig. 4.
- Fig. 3 and Fig. 19.
- Scale alone is not the mechanism enabling rare-task learning; multi-task methods can also enable itclaim0.757Clarification in related work.
- Mechanism from Theorem 4.
- Data-induced competition over resources.
- Counter-example disproving that architectural sparsity alone can prevent polysemanticity
- Central conclusion.
- Key cross-modal alignment result