Unverified50% confidenceDecision RuleExact time
Moving the baseline (raising or lowering the average recall@5 threshold) requires an explicit ADR decision, rather than being changed just to make CI green.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedWhen recall@5 on adversarial questions is low, the correct action is to go back and check the chunking strategy; only after recall@5 meets the bar is it meaningful to invest in optimizing the embedding model or reranker.62% similarUnverifiedThe gate uses only recall@5 as a hard threshold, with MRR and nDCG@5 as observational metrics, to avoid ranking fluctuations causing unstable builds.62% similarUnverified自适应层归一化（AdaLN）由DiT架构推广，将条件信号通过MLP映射为缩放和偏移参数，相比交叉注意力计算开销更低60% similarUnverifiedPrediction-based scheduling can significantly reduce response latency and over-provisioning compared with traditional threshold-triggered autoscaling.60% similarUnverifiedSetting the timeout below the observed p95 means deliberately giving up about 5% of calls in exchange for a bounded loop duration; whether this trade-off is acceptable depends on whether the task can tolerate skips.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069284API
curl https://kongchang.com/api/v1/knowledge/claims/1069284MCP
get_claim(id=1069284)