Menu

#Sinkhorn

1 post

Feed
1 of 1 post
Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM": The Decoy Trap, Dual-SVC & Sequence Encoders
📰
0Read More

Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM": The Decoy Trap, Dual-SVC & Sequence Encoders

DEV Community: datascience·Jun Matsui·9 days ago
#qlP7bAGB
#devtodatascience#science#devto#dev#flash

How we de-camouflaged public SOTA notebooks, added DeBERTa-v3 sequence classification, recalibrated soft Sinkhorn balancing, and applied deterministic typography invariants to push beyond 0.672 into Top 5.

15s