Unverified50% confidenceFactExact time
This study is a pre-registered study using 8 random seeds (6 of which were unseen at freeze time) and employing artifact-aware scoring and TOST equivalence tests.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
Unverified通过固定随机种子（Seed）可以提升测试的确定性79% similarUnverified作者建议的组合策略是用至少5个随机种子分别训练基线和提出方法，报告准确率均值和标准差配合配对检验，并对代表性种子额外运行 McNemar 检验展示样本级预测分歧72% similarUnverifiedThe paper constructs a diagnostic experiment using one-step pushing, validated with 32 random seeds.71% similarUnverifiedThe paper reports a pre-registered study that tested four predictors on two datasets, in which all seven confirmatory certificates were positive, and the eighth pair failed the pilot.70% similarUnverifiedThe study's evaluation protocol repeated evaluations using 8 different rollout seeds for the pretrained backbone and all 11 training methods.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138291API
curl https://kongchang.com/api/v1/knowledge/claims/1138291MCP
get_claim(id=1138291)