Connected Papers vs Semantic Scholar: pricing, features and which to choose

Connected Papers is a visual literature discovery service for researchers, students, and applied scientists who begin with a paper they already know. A user enters an origin paper and receives a map of related research, making the product useful for orientation before deeper reading. It publicly launched after beta in June 2020. Its About page links team profiles but does not state current headcount or funding. A 2022 announcement said the service was building more than 50 graphs per minute and had reached more than two million researchers in the prior year, which are historical company claims. The product remains active and focused on discovery rather than drafting. Its main tradeoff is convenience versus coverage, since a visual neighborhood can clarify a field without representing every relevant publication.

The workflow begins with a paper title or identifier, then Connected Papers analyzes a surrounding corpus and presents a force-directed graph of strongly related papers. Node size indicates citation influence, color indicates recency, and line strength indicates similarity. Prior Works highlights common ancestors, while Derivative Works surfaces later studies and reviews. Multi-origin graphs refine discovery around several seed papers, and saved papers plus history support repeated sessions. This workflow helps students understand intellectual structure, trace foundations, locate later extensions, and find review papers that may be missed by a single keyword query. It also shifts effort from query construction to result interpretation. Each promising item still requires independent reading, source checking, and confirmation that the apparent relationship is substantively relevant.

Connected Papers is a strong choice for orientation, citation chaining, and finding intellectual neighborhoods around a known paper. ResearchRabbit is broader for collections, author following, and ongoing monitoring, Litmaps emphasizes tracking and alerts, and Semantic Scholar provides conventional search; OpenAlex and Inciteful are additional alternatives. Connected Papers is not a complete search system because graph similarity is not keyword recall, corpus coverage is bounded, and the service cannot replace full-text access, screening, duplicate handling, or source verification. Pick it when a visual map is the fastest way to understand a field or extend a seed-paper search. For systematic reviews, use it alongside explicit database searches, inclusion criteria, screening records, and reference checking so visual prominence does not determine coverage alone.

Semantic Scholar is a free scholarly search and discovery service developed by the Allen Institute for Artificial Intelligence, or Ai2, a nonprofit research institute founded in 2014. The service launched in 2015 and indexes more than 200 million academic papers, while its product page reports a searchable corpus exceeding 214 million papers. Ai2 describes the service as a research and product development team using machine learning to process and classify papers. The organization also publishes open code and datasets. Its public resources include the Semantic Scholar Academic Graph and the Semantic Scholar Open Research Corpus, giving researchers and developers access to structured scholarly data alongside the hosted search experience.

A typical workflow starts with a keyword search across papers from all scientific fields, then narrows results by journal, conference, author, publication type, or date. TLDR summaries provide short descriptions for nearly 60 million papers in computer science, biology, and medicine. Users can inspect highly influential citations, export BibTeX, MLA, APA, or Chicago references, and save papers into library folders. Research Feeds learn from saved papers and relevance ratings to recommend additional work and send email alerts. Ask This Paper can answer questions with supporting statements on a limited set of English-language papers. Semantic Reader adds citation cards, tables of contents, definitions, and highlighted goals, methods, and results for many arXiv papers.

Semantic Scholar is strongest as a broad, free discovery layer and metadata service, but it does not grant permission to reuse papers and does not endorse claims made in indexed publications. Its FAQ says it has no smartphone app, and some AI features remain limited by language, corpus, or beta status. Google Scholar offers another broad search index, while OpenAlex provides an alternative open scholarly data service and Scopus targets paid bibliometric workflows. Semantic Scholar is the better pick for researchers who want AI-assisted discovery without a subscription and developers who need accessible scholarly metadata, provided they can work within API limits and licensing terms.