Unverified50% confidenceFactExact time
Early GCNs are essentially transductive—they require seeing the complete graph structure during training and cannot handle new nodes that did not appear in the training set during inference.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedZhipu did not retrain the model base, but retained GLM-5.2's base and only expanded and reinforced it during the post-training phase.69% similarVerifiedThe GLM series originally adopted an autoregressive blank-filling pre-training framework that accommodates both understanding and generation capabilities.69% similarVerifiedEarly GLM adopted Autoregressive Blank Infilling as its pre-training objective69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/914030API
curl https://kongchang.com/api/v1/knowledge/claims/914030MCP
get_claim(id=914030)