[KongchangAI]
Unverified50% confidenceFactExact time

The experiment used 7,606 TypeScript/JavaScript files deduplicated by exact hashing and trained byte-level BPE tokenizers with vocabulary sizes of 2k, 8k, 16k and 32k respectively, with all tokenizers trained on the same byte sequence.

1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1019335
API
curl https://kongchang.com/api/v1/knowledge/claims/1019335
MCP
get_claim(id=1019335)