Unverified50% confidenceFactExact time
Polarity matters more than familiarity: even pairings that Laya never output during training (such as absent/present) still raised the flip rate by 41 percentage points compared with neutral names.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe source-anchored variant proposed in the paper further reduces source feature displacement by 47.7% to 83.6% compared to purely learned transfer, while preserving most of the alignment gains63% similarUnverified63%的提升幅度是相对于基线的相对提升，而非绝对准确率的提升63% similarUnverifiedAfter matched supervised training, model performance improved to 99.8%, while removing the relational links caused accuracy to plummet to 23.4%, even below the best shortcut's 27.0%.62% similarUnverifiedThe model's generalization ability on fonts never seen during training is approximately 59% top-1, only 6 points below the 65% achieved on seen fonts.61% similarUnverifiedWhen targeting a 5% goal, the miss rate on the held-out set can reach as high as 17%, indicating that threshold performance on training data cannot be directly extrapolated.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029246API
curl https://kongchang.com/api/v1/knowledge/claims/1029246MCP
get_claim(id=1029246)