- 5 graphs per month
- All features included
Connected Papers turns a paper identifier, URL, or title into a visual graph of similar academic papers. Researchers can explore a field’s trends, discover important recent papers, and use Prior Works and Derivative Works views to find influential earlier studies and later literature reviews. It draws on the Semantic Scholar database, which covers papers across scientific fields, and can help users fill gaps in a thesis bibliography.
Promote this Tool
Update this Tool
Connected Papers
Connected Papers turns a paper identifier, URL, or title into a visual graph of similar academic papers. Researchers can explore a field’s trends, discover important recent papers, and use Prior Works and Derivative Works views to find influential earlier studies and later literature reviews. It draws on the Semantic Scholar database, which covers papers across scientific fields, and can help users fill gaps in a thesis bibliography.
Ads
What is Connected Papers?
Connected Papers helps users explore academic literature through visual graphs built from a starting paper. Enter a DOI, arXiv identifier, paper URL, or title to generate a graph of similar papers and get an overview of a research field. The graph can help reveal trends, popular works, and relevant papers that may otherwise be missed. Prior Works provides a way to find important ancestor papers, while Derivative Works highlights literature reviews and newer state-of-the-art work that followed the input paper. Users can follow interesting papers and build additional graphs to explore further. The service uses the Semantic Scholar database, which contains papers from scientific fields including machine learning, biology, and philosophy. It is also intended to help researchers fill gaps in a thesis bibliography.
Who will use Connected Papers?
- Academic researchers
- Applied scientists
- University students
- Thesis writers
- Researchers exploring a new scientific field
How to use the Connected Papers?
- Step1: Enter a paper DOI, arXiv identifier, paper URL, or paper title.
- Step2: Build a graph from the input paper to see similar academic papers.
- Step3: Explore the graph to understand relevant works and trends in the field.
- Step4: Use Prior Works to find influential ancestor papers and Derivative Works to find later reviews and research.
- Step5: Open interesting papers and build additional graphs to continue exploring or fill bibliography gaps.
Platform
- Web
Connected Papers's Core Features & Benefits
The Core Features
- Generate a visual graph of papers related to a starting paper
- Accept a DOI, arXiv identifier, paper URL, or title as input
- Explore prior works and derivative works
- Use Semantic Scholar’s academic paper database
- Build additional graphs from papers discovered during exploration
The Benefits
- Get a visual overview of an academic field
- Discover relevant or important recent papers
- Find influential earlier research and later literature reviews
- Identify papers to include in a thesis bibliography
Connected Papers's Main Use Cases & Applications
- Exploring an unfamiliar academic field
- Finding important recent papers in fast-moving areas such as machine learning
- Identifying prior research and influential ancestor papers
- Finding derivative works, literature reviews, and newer research
- Filling gaps in a thesis bibliography
Connected Papers's Pros & Cons
The Pros
Creates visual graphs to make relationships among related academic papers easier to explore
Supports multiple starting inputs, including DOI, arXiv identifier, URL, and title
Includes dedicated Prior Works and Derivative Works views
Covers scientific research across fields through the Semantic Scholar database
The Cons
The workflow starts from an academic paper identifier, URL, or title, so users need a relevant seed paper
Results rely on coverage in the Semantic Scholar database
Its scope is academic literature discovery rather than general-purpose web research
Connected Papers's Pricing
| Has free plan | YES |
|---|---|
| Free trial details | |
| Pricing model | freemium |
| Is credit card required | No |
| Paid from | 6 USD |
| Has lifetime plan | No |
| Billing frequency | quarterly/yearly |
Details of Pricing Plan
Free
0 USDAcademic
6 USD- Unlimited graphs
- All features included
- For academics, non-profits and personal use
- Billed $72 annually
Academic Group
6 USD per seat- Unlimited graphs
- All features included
- Single invoice
- For academics and non-profits
- Billed $72 per seat annually
Business
20 USD- Unlimited graphs
- All features included
- For business and industry
- Billed $240 annually
Business Group
20 USD per seat- Unlimited graphs
- All features included
- Single invoice
- For business and industry
- Billed $240 per seat annually
FAQs of Connected Papers
Connected Papers Company Information
- Website:
- Company Name: Connected Papers
- Support Email:
- Facebook:
- X(Twitter):
- YouTube:
- Instagram:
- Tiktok:
- LinkedIn:
Connected Papers Reviews
5/5
Connected Papers's Main Competitors and alternatives?
Google Scholar
Semantic Scholar
ResearchGate
PubMed
Mendeley
You may also like:
Refly.AI empowers non-technical creators to automate workflows using natural language and a visual canvas.
Resea AI is an intelligent research AI agent that autonomously completes research and writing tasks quickly.
Moody's Research Assistant offers insightful analysis and research capabilities for financial professionals.
MARL-DPP implements multi-agent reinforcement learning with diversity via Determinantal Point Processes to encourage varied coordinated policies.
A Python-based framework enabling creation and simulation of AI-driven agents with customizable behaviors and environments.
A Python-based multi-agent simulation framework enabling concurrent agent collaboration, competition and training across customizable environments.
Deep Research Agent automates literature review by retrieving, summarizing, and analyzing scientific papers using AI-driven search and NLP.
An AI agent framework orchestrating multiple translation agents to generate, refine, and evaluate machine translations collaboratively.
An AI-powered agent that autonomously browses web pages, extracts data, and generates structured research summaries.
An AI agent that automates academic and web research by searching, summarizing, and synthesizing information into structured reports.
An AI-driven agent automating deep research tasks: web scraping, literature summarization, and insight generation for efficient analysis.
An RL-based AI agent that learns optimal betting strategies to play heads-up limit Texas Hold'em poker efficiently.
An agent-based simulation framework for demand response coordination in Virtual Power Plants using JADE.
An autonomous AI Agent that performs literature review, hypothesis generation, experiment design, and data analysis.
AI agent that performs automated web research, gathering, summarizing, and extracting insights from multiple online sources quickly.
AI_RAG is an open-source framework enabling AI agents to perform retrieval-augmented generation using external knowledge sources.
Open-source Python framework implementing multi-agent reinforcement learning algorithms for cooperative and competitive environments.
An open-source AI agent that integrates large language models with customizable web scraping for automated deep research and data extraction.