Unverified50% confidenceFactExact time
BranchOPD leverages the student model's own uncertainty and the divergence between the teacher and student to locate the decision points most worth branching.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn Squint OPSD, the teacher's token-level distribution supervises the student model's learning along the on-policy trajectory.68% similarVerifiedKnowledge distillation, proposed by Hinton et al., has student models inherit implicit knowledge by learning from the soft probability distributions output by teacher models.63% similarUnverifiedRequiring students to demonstrate their thinking process, drafts, revision history, and to explain their reasoning can shift the grading focus from answers to process.62% similarUnverified教育场景的Agent强调苏格拉底式引导，不直接给出答案而是通过追问帮助学生建立自主推理能力61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001135API
curl https://kongchang.com/api/v1/knowledge/claims/1001135MCP
get_claim(id=1001135)