Unverified50% confidenceBenchmarkExact time
On the temporal split test set (878 comparisons from 655 trials), a gradient-boosted emulator trained on registry data eliminated about one-fifth of the error of a simple baseline.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/5/2026
First Seen
Valid until: 2/3/2027
Sources
Related Entities
Related Claims
Unverified实验采用8:2比例划分数据,20%作为内部测试集,训练集内部使用5折交叉验证,并移除重复记录以避免数据泄漏79% similarUnverifiedThe total of 2167 multiple-choice questions and 999 experimental records is still insufficient for training a large-scale generative model, and is better suited as an evaluation benchmark or fine-tuning seed.75% similarUnverifiedLargha-150M-v1's training mixture includes a pool of 500 error corrections, which were mined from the model's predictions on typed-decision test rows, so 0.906 is a fitting reading rather than a zero-shot result.75% similarUnverifiedUnder the multi-pass training mode, overall submission calibration error decreases by 63%–68%.72% similarVerifiedIn the experimental design, the AI used an 8:2 split to reserve 20% as an independent test set, and applied 5-fold cross-validation on the 80% training set to avoid data leakage.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137966API
curl https://kongchang.com/api/v1/knowledge/claims/1137966MCP
get_claim(id=1137966)