Unverified50% confidenceBenchmarkExact time
The learning curve shows that vertical writing layouts cannot be solved by adding data: 8.7% with zero training samples, 84.7% with 800 sheets, and 89.3% for both 2400 and 3000 sheets.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen sampling eight candidates without constraints from the model, 10.2% of inputs cannot produce any valid output under limited training data, and this proportion drops to 0.4% when using the full training data79% similarUnverifiedOn repeated questions, index reinforcement raised the top-1 hit rate from 0.571 to 0.743 without any model training throughout the process.72% similarUnverifiedAfter 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)69% similarUnverifiedGradient boosted trees trained on the same data captured only 57.5% of actual payment dates within their 80% intervals, noticeably lower than TabPFN's 79.1%.67% similarUnverified负采样将每步训练的复杂度从O(V)降低到O(k)，k是负样本数（通常取5-20）67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036991API
curl https://kongchang.com/api/v1/knowledge/claims/1036991MCP
get_claim(id=1036991)