Unverified50% confidenceFactExact time
All twelve pairs of comparisons exceeded the pre-specified threshold margin, and the complete pre-registered behavioral criterion was passed.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
Unverified半监督目标检测方法在COCO等基准上利用10%标注数据结合大量未标注数据，性能可接近全量监督训练水平61% similarUnverifiedIn code generation evaluation, pass@1 measures the probability that the model passes the test with a single generation, while pass@10 allows the model to make 10 attempts and takes the best result60% similarUnverifiedThe research team selected 8 models spanning different capability tiers and conducted cross-evaluations across 54 benchmarks59% similarUnverifiedThe experiments were tested across six heterogeneous benchmarks.59% similarUnverifiedThe experiment tested 15 frontier models.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928329API
curl https://kongchang.com/api/v1/knowledge/claims/928329MCP
get_claim(id=928329)