Automatically extracts and indexes citations from documents.
Searches within the full text of documents, not just metadata.
Extracts bibliographic information like authors, titles, and abstracts.
Groups similar documents together based on content.
Distinguishes between authors with similar names.
Provides free access to a vast collection of scientific papers.
Allows filtering by date, author, citation count, and more.
Researchers use CiteSeerX to find and review existing literature on specific topics in computer science.
Analyze citation patterns to identify influential papers and authors in the field.
Discover new and relevant research papers based on search queries and recommendations.
Conduct studies on publication trends, research impact, and academic metrics.
Build profiles of researchers based on their publications, citations, and co-authorships.
Students gather sources and references for their theses and dissertations.
Identify potential collaborators by exploring co-authorship networks and related work.
Assess the relevance and impact of journals for paper submission decisions.
Find prior art and related research in technology fields for innovation and IP purposes.
Educators use it to find materials for courses, lectures, and academic assignments.
Track emerging trends and hot topics in computer science research over time.
Use citation data to manage bibliographies and references for academic writing.
Sign in to leave a review
Arxiv-sanity is an innovative web platform that enhances the arXiv repository by integrating machine learning for personalized paper recommendations. Created by AI researcher Andrej Karpathy, it helps academics and researchers efficiently discover and manage scientific publications. The tool uses algorithms like TF-IDF and collaborative filtering to analyze user preferences and suggest relevant papers from arXiv's vast database. Key functionalities include a personal library for saving papers, advanced search with filters by date, category, and citations, trend visualization to track popular topics, and similarity search to find related works. It is particularly valuable in fast-paced fields such as artificial intelligence, computer science, and physics, enabling users to stay updated with the latest research without manual browsing. The interface is designed for ease of use, allowing quick access to abstracts, PDFs, and metadata. By automating paper discovery, Arxiv-sanity saves time and improves research productivity, making it an essential tool for students, professionals, and enthusiasts in the scientific community.
Connected Papers is an AI-powered tool designed to assist researchers, academics, and students in visualizing and exploring connections between academic papers. By inputting a seed paper via title, DOI, or author, the tool generates an interactive graph based on citation networks, highlighting related works and seminal references. This visualization aids in comprehensive literature reviews, discovery of new research areas, identification of trends, and gap analysis. Utilizing advanced algorithms to analyze bibliographic data, Connected Papers streamlines the research process, saving time and enhancing productivity. It supports features like filtering, exporting, and customizable views, making it a valuable resource for evidence-based inquiry across various disciplines.
Elicit is an AI research assistant designed to help academics and students explore scholarly literature more efficiently. Built initially by Ought, it can search research databases, cluster and summarize papers, extract key information from PDFs, and help generate structured literature reviews. Instead of manually combing through endless search results, users can ask research questions and see relevant papers organized by outcomes, methods, and other attributes. Elicit does not replace careful reading or methodological judgment, but it significantly accelerates early-stage scoping, hypothesis generation, and evidence mapping, making it particularly valuable for thesis work, systematic reviews, and policy or product research projects that rely heavily on academic papers.
