Unverified50% confidenceFactExact time
According to Bayesian decision theory, the optimal decision threshold t* satisfies t* = C(FP) / (C(FP) + C(FN)).
1
Sources
50%
Confidence
Long-term
Relevance
8/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTop-p (nucleus sampling) dynamically truncates to the smallest set of tokens whose cumulative probability exceeds the threshold p.57% similarUnverifiedFP8 has two variants: E4M3 (4-bit exponent + 3-bit mantissa), which has higher precision and is suited for forward inference, and E5M2 (5-bit exponent + 2-bit mantissa), which has a larger dynamic range and is suited for gradient computation.57% similarUnverifiedEckart-Young定理保证截断SVD是Frobenius范数意义下的最优秩r近似56% similarUnverifiedThe core formula of HN's ranking algorithm is roughly Score = (P-1) / (T+2)^G, where P is the number of votes, T is the number of hours since posting, and G is a gravity parameter of approximately 1.8.55% similarVerifiedTop-P (nucleus sampling) samples from the smallest set of tokens whose cumulative probability exceeds the threshold P, while Top-K selects only from the K candidates with the highest probabilities.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823678API
curl https://kongchang.com/api/v1/knowledge/claims/823678MCP
get_claim(id=823678)