[KongchangAI]
Unverified50% confidenceSolutionExact time

作者发现只用 batch 范围内的全局 -λ·ECE 惩罚几乎不起作用,因为它会被 PPO 或 GRPO 的 baseline 直接吸收抵消

1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/956117
API
curl https://kongchang.com/api/v1/knowledge/claims/956117
MCP
get_claim(id=956117)