Each CSV file has two rows: ‘winner’ and ‘loser’. Each column has both winner and loser object ID.
If you use our dataset in your papers, please cite the following paper:
Ryusuke Takahama, Toshihiro Kamishima, Hisashi Kashima, “Progressive Comparison for Ranking Estimation”, in Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), 2016, pp. XX-XX.
Ryusuke Takahama, Kyoto University.