Unverified50% confidenceFactExact time
Hydrogen-1.0's training method combines supervised fine-tuning (SFT) with reinforcement learning (RL), with data sources including domain data, scientist feedback, in-house laboratory records and discovery trajectories.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHydrogen-1.0's training data includes domain data, laboratory records and agent discovery trajectories.79% similarVerified从预训练检查点到可商用产品需经历监督式指令微调(SFT)和基于人类反馈的强化学习(RLHF)两个后训练阶段73% similarUnverifiedHydrogen-1.0 chose post-training from GLM-5.3 rather than training from scratch, following a "base model + domain specialization" route.72% similarUnverifiedRLHF (Reinforcement Learning from Human Feedback) is a key technology used to train ChatGPT.68% similarUnverifiedBy constructing supervisory signals from the data itself, self-supervised learning has become the core training strategy for large-scale pre-trained models such as BERT, GPT, and MAE.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134460API
curl https://kongchang.com/api/v1/knowledge/claims/1134460MCP
get_claim(id=1134460)