Unverified50% confidenceFactExact time
DiscoBench最终生成211个测试样本，包含463个歧义实例
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
Related Claims
UnverifiedThis test generated a total of 147 model calls.56% similarUnverifiedThe model ultimately outputs a tensor of 201×18×4, where 4 represents 4 lane lines, 18 represents key rows, and 201 represents 200 grid positions plus 1 non-existence class.54% similarUnverified叠加cv=5的5折交叉验证后，144种参数组合需训练144×5=720次模型53% similarUnverifiedIn the benchmark tests, each repository was run 4 times on each side and the median was taken.52% similarUnverifiedSol scored 9019 points on the Terminal Bench 2.1 programming benchmark.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/396699API
curl https://kongchang.com/api/v1/knowledge/claims/396699MCP
get_claim(id=396699)