Unverified50% confidenceFactExact time
The reconstruction loss only compares predictions with ground truth inside the hole; the mask M zeros out pixels the network has already seen, preventing the model from scoring by copying the context.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter switching to greedy decoding, the final model frequently fell into loops, a failure mode that was completely invisible in the validation loss68% similarUnverifiedMultiplying the unlearning loss of the forget set by 0.0 causes the forget items to produce no gradients, meaning the model performs no real unlearning updates.66% similarUnverified纯坐标/模板匹配方案对版式变化零容忍，供应商调整发票版式或增减行列会导致解析全面崩溃65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004199API
curl https://kongchang.com/api/v1/knowledge/claims/1004199MCP
get_claim(id=1004199)