Unverified50% confidenceFactExact time
GNoME基于图神经网络（GNN），通过学习Materials Project等密度泛函理论（DFT）数据库中已知晶体结构稳定性规律进行预测
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
The Real Bottleneck in Materials Innovation: Why Scaling Up Is Harder Than Discovery
hackernewshackernews7/10/2026
Related Claims
UnverifiedGNoME采用主动学习策略，迭代式地生成候选、预测稳定性、筛选最有价值结构送入DFT计算验证，再更新模型75% similarUnverifiedResearchers use graph neural networks (GNN) to learn neutronics simulations of breeding blankets, enabling sub-second prediction of TBR values for arbitrary combinations of geometric parameters with prediction errors controlled within 1%.69% similarUnverifiedThe output of GNoME is essentially a prediction of thermodynamically potentially stable structures, and does not incorporate engineering considerations such as synthesis pathway design, kinetic stability, impurity tolerance, or process windows.68% similarUnverifiedHNSW的核心思想借鉴六度分隔理论，通过构建多层跳表网络以对数级复杂度逼近线性扫描的准确率62% similarUnverifiedGLM 5.2 represents an important milestone for Zhipu on the evolutionary path of reasoning capabilities, context window expansion, and multimodal integration62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487667API
curl https://kongchang.com/api/v1/knowledge/claims/487667MCP
get_claim(id=487667)