{
  "id": 7646,
  "url": "https://arxiv.org/abs/2603.05295v3",
  "title": "WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces",
  "summary": "We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverage of complex, high-value tasks often missed by synthetic methods. Leveraging this dataset, we propos",
  "authors": "Sicheng Fan, Rui Wan, Yifei Leng, Gaoning Liang, Li Ling, Yanyi Shang et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-05T15:37:34.000Z",
  "fetched_at": "2026-07-14T16:33:21.051Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7646",
  "original_url": "https://arxiv.org/abs/2603.05295v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}