CiteSeerX

CiteSeerX is a public search engine and digital library for scientific and academic papers, primarily in the fields of computer and information science. It aims to improve the dissemination of scientific literature and advance the field of scientific literature digital libraries.

Key features of CiteSeerX include:

• Autonomous Citation Indexing: It automatically extracts citations from research papers found on the web, creating a citation graph that allows users to track the influence and evolution of ideas.
• Citation Context: CiteSeerX attempts to provide the context in which a paper is cited, allowing users to understand how the cited work is being used and evaluated.
• Similar Document Retrieval: Based on citation patterns and content analysis, CiteSeerX can identify documents that are similar to a given paper.
• Author Identification: It attempts to identify and disambiguate authors based on their names and affiliations, grouping together publications by the same individual.
• Open Access: CiteSeerX is freely accessible and allows users to download research papers (subject to copyright restrictions).

CiteSeerX relies on web crawlers and automated algorithms to gather and process information. While it offers a valuable resource for researchers, it's important to note that the accuracy of its citation indexing and author identification can vary. Users should always verify the information found on CiteSeerX with the original sources. The project was developed at Pennsylvania State University.