Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Leakage and the Reproducibility Crisis in ML-based Science


Jul 14, 2022
Sayash Kapoor, Arvind Narayanan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning


Apr 06, 2022
Jessica Hullman, Sayash Kapoor, Priyanka Nanayakkara, Andrew Gelman, Arvind Narayanan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mitigating dataset harms requires stewardship: Lessons from 1000 papers


Aug 06, 2021
Kenny Peng, Arunesh Mathur, Arvind Narayanan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems


Jul 28, 2021
Eli Lucherini, Matthew Sun, Amy Winecoff, Arvind Narayanan

* 17 pages, 5 figures; updated Figure 2(b) after fixing small bug in replication code (see Github for more details) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets


Apr 16, 2020
Angelina Wang, Arvind Narayanan, Olga Russakovsky

* Tool available at: https://github.com/princetonvisualai/vibe-tool 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Semantics derived automatically from language corpora contain human-like biases


May 25, 2017
Aylin Caliskan, Joanna J. Bryson, Arvind Narayanan

* 14 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Link Prediction by De-anonymization: How We Won the Kaggle Social Network Challenge


Feb 22, 2011
Arvind Narayanan, Elaine Shi, Benjamin I. P. Rubinstein

* 11 pages, 13 figures; submitted to IJCNN'2011 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email