finding
active
finding:turn-averaged-features-recover-outline-structure-automotive-domain-and-regulatory-compliance-in-the-blog-outline-per-token-finds-only-outline-and-lexical-featuresTurn-averaged features recover outline structure, automotive domain, and regulatory compliance in the blog outline; per-token finds only outline and lexical features
Example C.
Source paper
extracted_from(2026) · Kevin Der · Harish Kamath · Thompson, Ben
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central claim.
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.
- Prediction from coverage results.
- Example A.
- Example B.
- §5.5.
- LongBench v2 example E.
- LongBench v2 example D.
- Abstract.
- Turn-averaged features have highest embedding similarity 0.663 at k=3; per-token max lowest at 0.617finding0.788Consistent across k=1,2,3,5.