Unverified50% confidenceFactExact time
学术论文发表的因子在发布后平均衰减约32%（Harvey & Liu, 2020）
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Kronos金融基础模型：用AI读懂K线市场语言
Related Claims
UnverifiedResearch shows that approximately 15–25% of papers experience score changes after rebuttal, with positive changes slightly outnumbering negative ones68% similarUnverified2023年的分析显示主流LLM在生成学术引用时的错误率从30%到超过60%不等67% similarPartially VerifiedA 2023 study by Stanford University's Nelson Liu and colleagues found that when key information is placed in the middle of a long context, model performance can drop by more than 20%.67% similarUnverifiedA 2023 Stanford University study found that even the most advanced models at the time experienced a 30% to 50% drop in information-retrieval accuracy for middle segments when processing contexts exceeding 32K tokens.64% similarUnverifiedA 2023 Stanford University study showed that top LLMs have factual error rates as high as 20–40% in the medical and legal domains.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/599514API
curl https://kongchang.com/api/v1/knowledge/claims/599514MCP
get_claim(id=599514)