Unverified50% confidenceBenchmarkExact time
In all six 'domain × student model' combinations, Waypoint-OPD achieved the highest domain-average score among the compared methods.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedA study evaluated six knowledge tracing models on four public educational datasets and tested 12 threshold levels ranging from 0.50 to 0.99.62% similarUnverifiedBranchOPD outperforms both Vanilla OPD and the more expensive Multi-Rollout OPD (n=7) on all evaluation benchmarks.62% similarUnverifiedBy replacing the schema in the prompt with examples and normalizing enum values to lowercase before validation (using AI SDK's experimental_repairText), the pass rate of the 1B model can be improved from 1/10 to 6/10.61% similarUnverified在业务自动化评测中，相同单任务成本下Opus 5的通过率约为次优模型的1.5倍60% similarUnverifiedIn the specific experimental case, the overlapping-anchor scheme (n=912) showed the model at 55.2% versus the majority class at 51.1%, a net advantage of +4.1pp, about 2.4 standard errors; the non-overlapping-anchor scheme (n=163) showed 59.5% versus 54.0%, a net advantage of +5.5pp, about 1.4 standard errors.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046902API
curl https://kongchang.com/api/v1/knowledge/claims/1046902MCP
get_claim(id=1046902)