Unverified50% confidenceFactExact time
The scoring script checks three hard metrics: file count (default threshold: 8 files), lines changed (default threshold: 200 lines), and whether any blocked paths appear in the diff.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified评测设置了语义正确率、三次全对率和格式正确率三个维度指标62% similarUnverifiedSingle-turn tests use strict exact-parameter scoring weighted by severity (L4=8 points decreasing to L0=0 points).62% similarUnverified测试是IT四大方向（开发、测试、运维、网工）中入行门槛最低的60% similarUnverifiedThe author uses a weighted scoring scheme: in the outcome dimension, Pass scores 1.0, Partial scores 0.5, and Fail scores 0; severity weights are 4 for Critical, 3 for High, 2 for Medium, and 1 for Low.59% similarUnverifiedThe authors obtained 2,213 generation trajectories, 2,108 planning trajectories, and 2,013 rounds of validation improvement data from 4,003 candidates, which were used for supervised fine-tuning of Qwen3-8B-27B.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999944API
curl https://kongchang.com/api/v1/knowledge/claims/999944MCP
get_claim(id=999944)