Unverified50% confidenceBenchmarkExact time
For agent pairs with large reward gaps, the decision disagreement rate is below 1%.
1
Sources
50%
Confidence
Long-term
Relevance
9/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study found that the faithfulness score for counterfactual inputs was only 0.05 points lower than for factual inputs (on a 1–5 scale), a difference that is almost negligible.70% similarUnverified对比学习中的推远操作只要求负样本相似度低于正样本，并不要求达到-1的极端值70% similarUnverifiedUnder fixed compute, single-head attention scores 0.9 points lower than the optimal setting, and quality actually decreases when there are too many heads.69% similarUnverifiedEven when the correct value was retrieved, agents acted on it only 55% of the time, exposing a gap between retrieving information and acting on it.68% similarUnverifiedSingle-period data, lack of horizontal comparison, and differences in reporting standards mean that the 51% zero-payout data should be treated as a signal worth further investigation rather than a definitive judgment of the company.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/919804API
curl https://kongchang.com/api/v1/knowledge/claims/919804MCP
get_claim(id=919804)