01-cleaned-corpus.jsonl

{"sample_id":"clean-001","source_doc_id":"raw-001","lang":"zh","text":"Kubernetes 是一个用于自动部署、扩缩容和管理容器化应用的平台。","quality_score":0.95,"pii_removed":true,"dedup_group":"k8s-basic-001"}
{"sample_id":"clean-002","source_doc_id":"raw-002","lang":"zh","text":"工单系统 FAQ：客户反馈 ingress 访问 502，需要排查 upstream 是否健康。","quality_score":0.87,"pii_removed":true,"dedup_group":"ops-faq-014"}
{"sample_id":"clean-003","source_doc_id":"raw-004","lang":"en","text":"def add(a, b): return a + b","quality_score":0.89,"pii_removed":true,"dedup_group":"code-basic-003"}