Scim: Intelligent Skimming Support for Scientific Papers

PaperMage: A Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents

“…Today, it is being used in the production PDF processing pipeline to provide data for both the literature graph (Ammar et al, 2018;Kinney et al, 2023) and the paper-reading interface . It has also been used in working research prototypes which have since contributed to research publications (Fok et al, 2023b;. 6 We open-source papermage in hopes it will simplify research workflows that depend on scientific documents and promote extensions to other visuallyrich documents like textbooks (Lincker et al, 2023) and digitized print media (Lee et al, 2020).…”

“…Research papers and textbooks are central to the scientific enterprise, and there is increasing interest in developing new tools for extracting knowledge from these visually-rich documents. Recent research has explored, for example, AI-powered reading support for math symbol definitions(Head et al, 2021), in-situ passage explanations or summariesRachatasumrit et al, 2022;, automatic span highlightingFok et al, 2023b), interactive clipping and synthesis(Kang et al, 2022 * Core contributors; see author contributions for details.1 We use code snippets to illustrate our toolkit's core designs and abstractions. Exact syntax in paper may differ from the actual code, as software will evolve beyond the paper and we opt to simplify syntax when needed for legibility and clarity.…”

PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers

“…She also sees that there is a description for the Synergi paper and a paper she has collected in passing. By reading the description, she now recalls that "Scim: Intelligent Skimming Support for Scientific Papers" [17] supports paper reading by automatically highlighting important content in a paper and, unlike Synergi, there is no personalization component in the system. Compared to other traditional paper alert systems that only show a list of titles and, at most, abstracts, PaperWeaver helps the researcher figure out how each of the recommended papers connects to her topic of interest, as well as their nuanced relationships to papers she had already collected.…”