Paper 2605.22878
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
- Published
- May 2026
- Research lab
- Independent
- Citations
- 0
- GitHub
- 137 stars
01 In brief
Summary
SciAtlas is a large-scale, multi-disciplinary knowledge graph designed to support automated scientific research by organizing over 43 million papers from 26 disciplines into a structured topological network.
It contains 157 million entities (including papers, authors, institutions, keywords, topics, and fields) and 3 billion triplets, with 9 entity types and 12 relation types.
The graph is built from OpenAlex data, with keywords extracted using an LLM (Qwen3-30B-A3B-Instruct-2507) and semantic embeddings computed with bge-large-en-v1.5.
A neuro-symbolic retrieval algorithm combines keyword, semantic, and title matching with random walk with restart and graph reranking to enable deterministic association discovery.
The system supports applications such as literature review, idea grounding and evaluation, idea generation, research trend prediction, related author retrieval, and researcher background review.
SciAtlas aims to reduce reasoning costs and logical hallucinations compared to LLM-based deep research frameworks, with retrieval completed in under 2 minutes.
Future work includes CLI tools, integration of more knowledge forms, benchmarks, and dynamic updates.
02 From the paper
Abstract
The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on superficial keyword matching or vector-space semantic retrieval, which lack the topological reasoning capabilities required to navigate complex logical connections. Agentic deep-research-based frameworks are often prone to logical hallucinations and consuming high inference costs. To bridge this gap, in this report, we introduce SciAtlas, a large-scale, multi-disciplinary, heterogeneous academic resource knowledge graph designed as a panoramic scientific evolution network. By integrating over 43M papers from 26 disciplines, and a total of 157M entities and 3B triplets, SciAtlas provides a structured topological cognitive substrate that dismantles disciplinary barriers and furnishes AI agents with a global perspective. Furthermore, we develop a neuro-symbolic retrieval algorithm featuring tri-path collaborative recall and graph reranking, achieving a seamless transition from simple semantic matching to deterministic association discovery. We also present key application directions of SciAtlas, including literature review, automated research trend synthesis, idea positioning, and academic trajectory exploration, to demonstrate that SciAtlas can serve as an effective ``cognitive map'' to empower the full loop of automated scientific research while significantly reducing reasoning costs. We have released the interfaces for KG retrieval and various downstream tasks in our GitHub repo.