Unverified50% confidenceBenchmarkExact time
BlurPool can improve ResNet-50's shift consistency from approximately 89% to approximately 95%, while also yielding a small improvement in classification accuracy of about 0.5%.
1
Sources
50%
Confidence
Long-term
Relevance
8/30/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在从50%到92%的准确率提升中，REPL贡献最大（直接从50%跳至74%），随后领域知识注入、模糊搜索、公式追踪、系统prompt优化和bug修复层层累积66% similarUnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.65% similarUnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.64% similarUnverifiedLID accuracy at switching points is typically 10–20 percentage points lower than LID accuracy at non-switching points.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/825964API
curl https://kongchang.com/api/v1/knowledge/claims/825964MCP
get_claim(id=825964)