Unverified50% confidenceFactExact time
The self-test module scores students' answers on a 20-point scale.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the simplest items, the behavioral test overestimates faithfulness by as much as 20 percentage points.69% similarUnverifiedIn the scoring setup, only the lexical component, which accounts for 20% of the weight, is visible during the development phase, forming a partially observable objective.68% similarUnverified研究数据表明接受同伴教学的学生在概念理解测试中的得分比仅听讲座的学生平均高出20%-30%，且知识保留率更高66% similarUnverifiedEach question in the test is scored out of 100 points, consisting of 70 points for correctness plus 30 points for quality, with different questions carrying different weights.66% similarUnverifiedThe original Anthropic text recommends using a reranking model to narrow from the top 150 down to 20, and they tried passing 5, 10, and 20 chunks and found 20 worked best, but advise readers to test in their own scenarios.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1066366API
curl https://kongchang.com/api/v1/knowledge/claims/1066366MCP
get_claim(id=1066366)