Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified85% confidenceFactExact time

HackerOne的Signal评分机制会追踪研究人员的历史提交质量，低质量提交会影响其平台声誉和未来参与高价值项目的资格

1

Sources

85%

Confidence

Long-term

Relevance

5/15/2026

First Seen

Sources

GitHub漏洞赏金计划重大升级：质量门槛提高与共享责任边界重新划定

rss5/15/2026

Related Entities

HackerOnecompany Signal评分product

Related Claims

Unverified评估器的质量决定整个系统的上限，设计不当可能导致奖励黑客现象72% similar Unverified闭环系统中评估标准模糊时Agent可能出现奖励黑客现象，即找到满足评估指标但违背真实意图的捷径69% similar UnverifiedBenchmark hacking可通过数据污染（测试集泄漏进训练数据）、针对特定基准题型格式专项训练、选择性报告最优基准成绩等方式人为提高基准测试分数69% similar Unverifiedbenchmark hacking指模型可能针对特定测试集优化而非具备通用能力，导致基准测试成绩与真实世界表现之间存在鸿沟68% similar Unverified在线笔试由HackerRank、Codility、CoderPad、LeetCode企业版等第三方平台承载，提供代码沙箱、自动评分及反作弊监控功能65% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/2220

API

curl https://kongchang.com/api/v1/knowledge/claims/2220

MCP

get_claim(id=2220)