Evaluating Scite.ai as an Academic Research Tool

Jason A. Reuscher reviews Scite.ai

Posted on January 29, 2025 in Blog Posts

Core to the mission of Choice Reviews is providing succinct and helpful reviews of the newest academic resources to empower librarians to make the best selections for their collections. Over the years, we have expanded our understanding of academic resources from scholarly books to include electronic resources and database subscriptions. More recently, we have added to our offerings by reviewing AI tools. Librarians are often responsible for subscribing to or advocating for these tools and services, so we want to equip them to make smart decisions about what to purchase and why. Especially where AI is concerned, we want librarians to be able to “separate the tools from the toys,” to put it in Choice Editor and Publisher Rachel Hendrick’s words.

Inaugurating this new chapter of Choice Reviews, we wanted to share Jason A. Reuscher’s review of Scite.ai, published in the December 2024 issue of Choice. Reuscher is a Research and Instructional Librarian at Pennsylvania State University. Unlike generalist models such as ChatGPT and Google Gemini, Scite.ai was developed specifically for academic applications. It aims to expedite the research process by searching for citations and answering researchers’ questions. Reuscher’s review of Scite, posted below, details the many dimensions of this tool and evaluates its usefulness to academic researchers.

---

🔥 Stay up-to-date with LibTech Insights by signing up for our free newsletter. Just one weekly email with our new blog posts, top tech news stories, and other bonus content. Check out some posts from our archive:

• Beyond the Job Title: Digital Initiatives Librarian
• Microlearning and Micro-courses in Library Spaces
• Data Dilemmas: Sinnreich and Gilbert Examine the Impacts of Data

🦋 Choice is now on Bluesky. Say hi to us over there!

---

Review of Scite.ai by Jason A. Reuscher

Intended for undergraduates, graduates, faculty, and professional researchers, Scite.ai delivers an interface that creates smart citations. These citations can be searched by title, author, keywords, or DOI and are accessed through either .pdf or xml formats through pre-existing agreements with key publishers (Wiley, Cambridge University Press, Karger, Wolters Kluwer, Thieme), preprint servers (arXiv, bioRxiv, and medRxiv), and other established societies, presses, universities, laboratories, and publishers.

Smart Citations are generated using the following steps: access, detection, extraction, and internal tracking. Each citation generated then contains information about which papers are citing each other, the explicit context (the written or textual context) between the citation and the location of the paper that is cited, and a classification heuristic which categorizes whether the citation supports, mentions, or contrasts the cited work’s claims.

Some citations do remain unclassified, however. All of the categories (with the exception of the unclassified) are represented with icons that are easy to differentiate from each other on the results page. Clicking on an article title reveals a full citation report, which lists a given article’s references, the number of articles that cite it, and how many are supporting, mentioning, contrasting, and unclassified. The results can be sorted or ordered by engagement, editorial concern, most cited/least cited, most supported/least supported, most contrasted/least contrasted, most recent/least recent.

While citation counts, linked references, and cited-by metrics are not new, the contextualization is worth a further look as a reference and research tool. The quantification and ordering of citations directly impact the role that academic librarianship plays in guiding users to reliable sources, as well as the librarian’s role in the creation, curation, and management of records and citations.

Other prominent features include Assistant (an AI chat assistant) and Reference Check (a tool which checks the reliability of an article’s references). The chat assistant works similarly to other AI chat platforms, but it documents the answers that it generates with verifiable sources. The range of topics that it can currently answer is strong within the STEM fields, but less so in the arts and humanities at this time. Scite.ai is packed with other features and customizations (custom dashboards, browser extensibility, embedded badges, saved searches, Zotero plugins, alerts, etc.), so it is worth investigating at an institutional level.

Individual price plans are $20.00/month with academic discounts available. Institutional or Team pricing is custom and based to some degree on a scaled, price-per-user formula.

Summary: Recommended. Upper-division undergraduates through faculty; professionals.

---

⭐️ Like this review? Learn more about subscribing to Choice Reviews at your library for up-to-date reviews of AI products and much more.

Related Posts