简体中文 · Markdown

English | 简体中文

AI4Science Observatory

Source-backed guides to scientific agents, remote laboratories and reusable AI4Science evidence.

Researchers and agents selecting scientific workflows, checking experiment access, or building a sourced literature table.

Start with three core guides, follow their primary sources, and reuse the JSON records. Pages are readable without login or JavaScript.

Three core guides

Question What you get
How to choose a scientific agent: literature, code, tools and experiments A task-first comparison of scientific agents, with source-backed examples and a reusable selection checklist.
How to connect an AI agent to a remote laboratory Distinguish real hardware from simulation, verify access and automation permissions, and preserve measurement provenance.
How to verify AI4Science claims and reuse research data A claim-to-source workflow, evidence labels, deduplication rules and a working read-only JSON example.

Agent entry points

Explore the collection

How to interpret the evidence

Guides distinguish primary-source descriptions, author-reported results and collection advice. Example templates are not measured results. Unknown access conditions do not imply free or permitted access. Cite the original paper for a scientific claim and this guide for its selection or curation method. Core guides and the Agent index have complete English and Chinese versions; most existing archive notes remain in Chinese.

Recent updates

Full update history