Home 2017-05-29T12:09:08+00:00


Here you can find the projects and publications of the Sciplore research group.

Our current projects:

If you are interested in working with us, e.g. during a student project or for compiling a thesis, please see our dedicated page at the University of Konstanz for project proposals.

Watch a video about our MindMapping software for researchers:


2305, 2014

Paid Internships in Tokyo, Japan for MS and PhD Students

By | May 23rd, 2014|Categories: SciPlore|0 Comments

We are offering two internships related to various research and software development projects at the National Institute of Informatics Tokyo – Japan’s premiere research institute in computer science.

Key Facts:
• Location: Tokyo, Japan
• Duration: minimum 2 months, maximum flexible
• Salary: approx. 170,000 JPY per month (sufficient to cover living expenses in Tokyo)

• Interns must be currently enrolled master or doctoral students.
• Background in computer science or related disciplines
• Motivation, curiosity, ability to work methodologically and independent

For more information on potential tasks or any other questions, please contact Bela Gipp (gipp@nii.ac.jp). Please include a short description of yourself, your background and the period in which you would like to do the internship.

1312, 2013

Apply for a Paid Internship at SciPlore – Summer 2014

By | December 13th, 2013|Categories: SciPlore|0 Comments

In cooperation with the German Academic Exchange Service (DAAD), we are offering a paid internship for a computer science Bachelor student, who is passionate about prototype design and development. Prerequisite is that you are a student studying at a German university. More details on prerequisites here, download the project description as PDF.

At SciPlore you will be working with an international team of researchers, affiliated with the University of California Berkeley and the University of Magdeburg in Germany. As an intern, you will have the chance to spend 6-12 weeks abroad at a research institute collaborating with the SciPlore team.

The SciPlore team develops novel approaches in citation and semantic text analysis for quantifying similarities between scientific articles. Similarity assessments are crucial to many Information Retrieval (IR) tasks, such as clustering of documents, recommending academic literature, or automatically detecting academic plagiarism.

Below is a screenshot of CitePlag – the first prototype of a citation-based plagiarism detection system, which we developed. To see for yourself the document similarity visualization of CitePlag, use the system on a real plagiarism case that translated from Chinese, or on a plagiarized medical publication that was retracted with the help of CitePlag.


Plagiarism Case by K.-T. zu Guttenberg

 Screenshot showing document visualization in CitePlag – click on the image to open the interactive web-based prototype

This internship with SciPlore is made possible by the German Academic Exchange Service (DAAD). To apply, simply create a profile with the DAAD on their RISE-Weltweit 2014 website and search for SciPlore’s project page in their database, which describes all the details of the internship project, including your tasks and the skills required.

Application deadline is January 12, 2014.

Compensation: The DAAD will provide you with a monthly stipend and a fixed payment to cover your travel expenses!

Berkeley – 1,000 EUR per month + 1,250 EUR onetime payment for travel expenses

If you have further questions please contact Bela Gipp at gipp@sciplore.org.


1810, 2013

CitePlag got a makeover

By | October 18th, 2013|Categories: SciPlore|0 Comments

CitePlag is the first prototype of a citation-based Plagiarism Detection (CbPD) System. The prototype was recently demonstrated at the SIGIR conference 2013.

What makes CitePlag novel?

In contrast to existing text-based approaches to plagiarism detection, CitePlag does not solely analyze literal text matches to determine document suspiciousness – but rather, CitePlag makes use of the unique citation placement in the full-text of documents to determine similarity and detect potential plagiarism.

In examining citation placement, position, and order, CitePlag forms a text-independent / and even language-barrier transcending “fingerprint” of the semantic content of documents, which can then be used to detect potential unoriginality and plagiarism.


CitePlag has come a long way from its humble beginnings in 2010, when we proposed the first citation-based approach to detect semantic similarity between documents for use in plagiarism detection. A year later, we developed the algorithms, and today we have a working prototype available for public use.

CitePlag now has a new user interface with improved functionality.

You can:

  1. upload your own files  (PDF/ text documents)
  2. examine recent plagiarism findings and examples of retracted plagiarism cases
  3. compare any two publications from the Open Access subset of PubMed’s database  (200,000+ medical publications)

Test the CitePlag prototype for yourself at its new home on the web: http://citeplag.org/

If you’re curious about the project, see our related publications or the doctoral thesis of Bela Gipp, which narrows in on all aspects of Citation-based Plagiarism Detection.

1502, 2012

First public version of Docear released (1.0 Beta 1)

By | February 15th, 2012|Categories: Beta, Docear, Release Notes|Tags: , , |7 Comments

Today, on February 15th, 2012 we released the first public version of Docear. It’s a Beta version and still has some bugs and missing features but overall it will give you a thorough impression of what we consider an academic literature suite should be.

The main idea behind Docear is that you annotate everything you consider important in a PDF. That means, you highlight text, write comments, or create bookmarks in the PDF. To create bookmarks and comments, you can use almost any PDF reader (highlighting text is a bit more complicated). These PDF annotations are then imported by Docear to a mind map. In this mind map you can organize all your annotations into categories, create further nodes and add more text. With the integrated reference manager, bibliographic data can be added to each of the PDF annotations (and all other nodes in the mind map). Subsequently, you can create a new mind map, drag e.g. a research paper, copy your annotations to the draft and if you need more information you just click on the PDF annotation and the PDF will open on the page the annotation was made. Watch this video to get a better idea of what Docear can do (watch it in full-screen mode). (more…)