Unverified50% confidenceBenchmarkExact time
True retrieval outperformed random neighbor retrieval by 0.97 points on the macro-average, but a paired task-level sign test did not establish a consistent advantage (p=0.067).
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified模板匹配的置信度阈值通常取0.8～0.95来判断是否找到目标68% similarUnverifiedThe study used Kendall's W statistic to measure ranking consistency across different tools, yielding W=0.07, p=0.83, which is almost indistinguishable from random coin flipping.67% similarUnverifiedIn the fact-updating task, the success rate of the embedding retrieval method fluctuated between 0.30 and 0.95, with a maximum gap of 0.45 across different random seeds.67% similarUnverifiedThe Mann-Whitney U test shows that task_score under the naive survival reward falls below the random-policy baseline, with p=0.012.66% similarUnverified在歧义点的四类行为中，'先搜再问'成功率最高，平均通过率达93.4%，远高于'直接猜'的56.5%，'搜多次再猜'为51.5%64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001101API
curl https://kongchang.com/api/v1/knowledge/claims/1001101MCP
get_claim(id=1001101)