Unverified50% confidenceBenchmarkExact time
On the PrimeVul held-out test set, REVA with GLM-5.3-Flash achieves 60.0% accuracy at about one second per function.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedReplay experiment: fixing the winning lr/wd schedule, without using PBT, and running on fresh initializations, 55/60 reached 95% accuracy; whereas with fixed hyperparameters at the geometric mean of that schedule, 0/60 succeeded.66% similarUnverified探索性能上界实验发现现有验证粒度并非最优，理想情况下计算量（FLOPs）可减少75倍，同时准确率提升1.1%65% similarUnverifiedQwen3.8 Flash Next has a sparsity rate of approximately 95%, using less than 5% of its parameters per inference.65% similarUnverifiedIn the benchmark test, Logistic Regression achieved 86.7% overall accuracy, 100.0% impact recall, and 0.0% cadence false positives.64% similarVerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102982API
curl https://kongchang.com/api/v1/knowledge/claims/1102982MCP
get_claim(id=1102982)