Using the Scholarcy Web Library
You can add PDF, Word, Powerpoint, HTML, XML, RTF, LaTeX, RIS and BibTeX files to your web library, and our AI engine will convert them into summary flashcards that you can store, export, share and annotate on any device. In addition to our Getting Started guide, here we provide more detail on the customisation options available in Scholarcy.
Documents can be imported into your Scholarcy Library in a number of ways. Within one of your chosen library folders:
- Click the green Import button and then:
- Expand the Drag and Drop upload panel, click on the drag area and select your files, or drag and drop files onto this area, then click the Upload file(s) button.
- Expand the Upload via web resources panel, then
- Paste a DOI or publicly accessible URL in to the Open access URL and click Import
- Click the GDrive upload or Dropbox upload button, log into your Google Drive or Dropbox account, and select the files you wish to import
- Expand the Plain text paste panel, paste your text into the text box, and click Upload.
- Via the Scholarcy Chrome Extension: click on the Save button at the top of the summary card created by the Extension. You may need to temporarily disable any adblocker extensions to enable this integration. The flashcard will be saved to your default My library.
- Via the Scholarcy Flashcard Generator: click on the Sign in to Save button at the bottom of the screen. The flashcard will be saved to your default My library.
We provide a range of options to help you customise the way Scholarcy processes your documents. To explore these, select Settings from the left-hand menu of the main screen and enable or disable the various options in the Import tab, as described below.

Summarisation settings
Structured summary
When checked, the AI will aim to structure the summary according to the structured of the source document, for example Introduction, Objectives, Methods, Results, Conclusion.
Rewrite in 3rd person
This rewrites the Scholarcy summary section into a neutral third person (for example ‘The authors’ results suggest …’) to make it easier to quote from and reference sections of the paper.
Summary length (words) or Percentage
This sets the length of the Scholarcy summary section of the flashcard. You can choose to have a summary with a fixed word limit set by the words option, or as a fraction of the original document set by the %option. If set, the % will override any value for the fixed word count. However, when the Structured summary option is checked, setting a target summary length will have less of an effect, depending on the structure and length of the original article.
Key points
This determines the number of items shown in the Scholarcy Highlights section of the flashcard. Between 5 and 10 is a good number to use here.
Summary engine
This can be set to v1, which gives a good result for a broad range of documents, or v2, which tends to work better for book chapters.

Engine settings
Extract figures
This extracts figures and their captions into a Figures section. You can then click on each figure to show a larger version in a new browser tab. Each Figure will be linked to callouts in the text. Figure extraction is very CPU intensive and, for large documents with high-resolution images, may not always be successful, so it is disabled by default.
Extract tables
This identifies tabular data and their captions, showing the captions in a Tables section along with a download button to save the tables to an Excel file on your computer.
Comparative analysis
This is an experimental feature that identifies and classifies citation contexts to show when the author is demonstrating how they build on previous work, contrast with the results of previous work, or confirm the findings of previous work.
PDF engine
Reflowing text in the correct order from PDF files is surprisingly difficult. The default, v1 setting is generally best for most PDFs. Changing this to v2 may give improved results on ‘difficult’ PDFs or those with margin line numbers such as preprints.
Image engine
If Extract figures is enabled, v1 works well for extracting figures consisting only of bitmap images. v2 works better if the figures contain a mix of bitmap and line images.