Unverified50% confidenceFactExact time
The recall formula is TP/(TP+FN).
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在二分类问题中召回率（Recall/Sensitivity）计算公式为TP/(TP+FN)，衡量模型识别所有真实阳性样本的能力79% similarVerifiedTPS (Tokens Per Second) is the core metric for measuring the inference speed of large language models, specifically referring to the number of tokens the model outputs per second during the generation phase.68% similarUnverifiedThe forward pass of an RNN is inherently sequential, with each step's computation depending on the output of the previous step, and computational complexity growing linearly with sequence length T as O[T].67% similarUnverifiedThe project efficiently computes the history vector P_t via zero-padded FFT linear convolution, keeping overall complexity at O(T log T).64% similarUnverifiedTime per output token (TPOT) measures the speed at which a model generates tokens one by one during the autoregressive decoding phase.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051079API
curl https://kongchang.com/api/v1/knowledge/claims/1051079MCP
get_claim(id=1051079)