Unverified50% confidenceFactExact time
Reef Infra's default selection strategy tallies the win-loss ratio across tasks and adopts a candidate strategy as long as it wins more tasks than it loses.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/25/2026
First Seen
Valid until: 12/24/2026
Sources
Related Entities
Related Claims
Unverified贝叶斯最优分类器在0-1损失下等价于选择后验概率最大的类别，回归问题中条件期望在平方损失下是最优预测63% similarUnverifiedThe core property of a strictly proper scoring rule is that the expected score is maximized if and only if the forecaster reports the probability they truly believe, with common examples including log-likelihood loss and the Brier score.62% similarUnverified对同一测试用例执行多次调用统计成功比例得到通过率，比二元的通过/失败判断更能反映模型真实表现62% similarUnverifiedInfoNCE 损失通过在一批候选中最大化正样本对相似度、最小化负样本对相似度进行训练，温度超参数τ越小分布越集中61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949277API
curl https://kongchang.com/api/v1/knowledge/claims/949277MCP
get_claim(id=949277)