Scite
external page Scite is a multidisciplinary, publisher-independent citation database that provides quantitative and qualitative insight into the way scientific publications cite each other.
Scite contains over 1.3 billion unique in-text citation statements, which are extracted and analyzed from more than 34.3 million full-text articles, as well as over 2 billion references, with a global coverage of more than 187 million research articles, books, reports, and preprints.
Various tools are available for simple and advanced searching, tracking, analyzing, extracting and visualizing research information, e.g.:
• Smart Citations: Provides an aggregate of contextual citation information: Citations are classified by a deep learning model trained to identify three categories of references: those that provide contrasting or supporting evidence for the cited work, and others that merely mention the cited document. Scite also extracts in which section of a document a reference occurred and displays the text snippet surrounding the citation.
The Scite Badge provides a quick overview and, in addition to the number of citations, also contains the respective classifications, as well as information on whether a document has been withdrawn or whether there are editorial notes (corrections, errata and expression of concerns) attached to it.
The Scite Badge is also available as a browser extension.
• Reference Check: Allows you to upload a text file (Word or PDF) and check the quality and reliability of the references it contains.
• Personal Account: Offers the possibility to create alerts and save searches. Using dashboards allows you to aggregate information from Scite or create such based on DOI lists and use it as a basis for further queries.
• Scite Assistant: A generative AI-powered research tool that provides answers and summaries to natural language questions, referencing the underlying sources. It offers a wide array of filters and settings to finetune it to the task at hand.
Update
Daily
Note
Scite uses artificial intelligence to provide the described services. It cannot be ruled out that it may generate results that could be considered false, misleading, biased, or even offensive. Users should not rely solely on AI-generated results but should conduct independent research and critically evaluate AI-generated output.
For more information on AI in teaching and learning, visit AI in Teaching and Learning | ETH Zurich.
Access
Access to this database is restricted to the ethz.ch domain due to licensing reasons. If you have any technical problems or questions about access rights, please contact the .
Courses
tbd
Tutorials
How Scite works: external page Scite: A smart citation index that displays the context of citations and classifies their intent using deep learning | Quantitative Science Studies | MIT Press
• external page Scite – Research Solutions Help & Support Center
Scite Data in a Nutshell, Source: Cordova, Jason, scite Coverage. Available at: external page scite Coverage – Research Solutions Help & Support Center (Accessed: 23.01.2025)