PulseAugur
实时 10:33:54
English(EN) Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms

Bluesky 审核系统在危害检测方面表现出高精确率但低召回率

一篇新发表在 arXiv 上的研究分析了 Bluesky 内容审核服务 (BMS),考察了 2025 年的 1060 万条审核标签。研究表明,BMS 作为一个人类-AI 协作系统运行,对色情和露骨内容的自动化标记速度很快,而更复杂的问题则需要人工监督且耗时更长。研究发现 BMS 的精确率很高 (0.837),但召回率很低 (0.222),这意味着它能准确标记其识别出的内容,但会漏掉大量有害信息。分析还识别出检测到的危害包括针对受保护群体的敌意以及传播露骨内容。 AI

影响 为理解社交平台上的 AI 辅助内容审核系统的运行有效性提供了见解。

排序理由 发表在 arXiv 上的研究论文,详细介绍了对某社交媒体平台审核服务的审计。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Bluesky 审核系统在危害检测方面表现出高精确率但低召回率

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发表在 arXiv 上的研究论文,详细介绍了对某社交媒体平台审核服务的审计。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Pushpdeep Singh, Sayeh Jarollahi, Ayan Majumdar, Vabuk Pahari, Abhijnan Chakraborty, Krishna P. Gummadi, Ingmar Weber, Abhisek Dash ·

    Bluesky 内容审核服务特征分析:从服务自动化到危害景观

    arXiv:2609.11373v1 Announce Type: cross Abstract: Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emergence of decentralized platforms with transparent, p…