SciDetect
=================================
SciDetect is a free software for detecting automatically generated academic papers. 
The software discovers text that has been generated with SCIgen and other fake-paper generators like Mathgen and Physgen.

Website: http://www.scidetect.forge.imag.fr

Source code (Git): https://forge.imag.fr/anonscm/git/scidetect/scidetect.git

References : Cyril Labbé, Dominique Labbé. "Duplicate and fake publications in the scientific literature: how many SCIgen papers in computer science?" Scientometrics 94, no. 1 (2013): 379-396 (online June 2012 - http://hal.archives-ouvertes.fr/file/index/docid/713555/filename/0-FakeDetectionSci-Perso.pdf)

Prerequisites
==================================
SciDetect was developed and tested on Ubuntu Linux.  It should work on
other system also.
To run ScidDetect, you will need Java SE 6 or higher. You will also need the following components:
-SciDetect_local.jar
-config.txt
-A directory for data samples.


Running
==================================
The main program is encapsulated in SciDetect_local.jar

For a summary of options, use the following command:
Java -jar SciDetect_local.jar -h

To check a folder contains PDF or XML, use the following command:
Java -jar SciDetect_local.jar -c path_to_folder

For more information, please refer to SciDetect_Doc.pdf file.


Makefile
==================================
SciDetect includes a makefile in case you want to recompile the program.
In a terminal window, simply navigate to the program directory and $make


Source code
==================================
See the program's Javadoc for a detail explanation of the source code.
 

Credits
==================================
SciDetect is a collaboration between Springer-Verlag GmbH and Universite Joseph Fourier (Grenoble France).
it was written by Nguyen Minh Tien and Cyril Labbe from the LIG (http://www.liglab.fr/?lang=en).


License
==================================
SciDetect is free software.  You are welcome to share, copy, and modify it, 
under the terms of the GNU General Public License, version 3.0.
See the LICENSE file for more details.