Unverified50% confidenceFactExact time
In the second experiment, certain papers were randomly assigned 5 initial selections among 20 social communities comprising 200 agents in total.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Claims
Unverified在5%显著性水平下测试100个随机因子，期望会有5个看起来显著（多重假设检验问题）67% similarVerifiedIn 2022, Hoffmann et al.'s Chinchilla paper redid experiments on four hundred models and concluded that, under the premise of compute-optimality, each parameter should correspond to approximately 20 tokens.66% similarUnverifiedWhen a team tests 1,000 combinations of strategy parameters, even if all combinations have zero predictive power, roughly 50 combinations will appear to perform excellently in backtesting purely due to randomness (the multiple comparisons problem).65% similarUnverifiedOn cognitive tasks, humans can achieve approximately 80%, while SOTA multimodal models achieve only 30% to 50%, sometimes approaching random guessing65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942718API
curl https://kongchang.com/api/v1/knowledge/claims/942718MCP
get_claim(id=942718)