Unverified50% confidenceBenchmarkExact time
In the study, the Full graph method achieved an SHD of 135 and an F1-score of 0.73, performing better in terms of structural distance.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe CAPI-DINO ViT-B/14 model achieved a linear probing accuracy of 68.7% on the iNat21 dataset.64% similarUnverifiedBraTS uses the Dice similarity coefficient (range 0–1, higher is better) and Hausdorff distance (lower is better) as unified evaluation metrics.63% similarUnverifiedVTracer was chosen because of its compact size (approximately 0.66 MiB) and because it produced the best vectorization results in baseline testing.61% similarUnverifiedVERGE improved precision from 0.764 to 0.849 and Matthews Correlation Coefficient from 0.681 to 0.73061% similarVerifiedThe larger the number of model parameters, the greater the robustness to quantization, allowing 70B-level models to maintain performance close to FP16 after 4-bit quantization.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975775API
curl https://kongchang.com/api/v1/knowledge/claims/975775MCP
get_claim(id=975775)