@inproceedings{satarifard2026semantic,
  title = {A semantic-based community model for high-fidelity tuning of olfactory mixture distances},
  author = {Satarifard, Vahid and Sisson, Laura and Han, Yikun and Ilídio, Pedro and Hladiš, Matej and Lalis, Maxence and Song, Xuebo and Yang, Tiffany and Yin, Wenjie and Ravia, Aharon and Zheng, CiCi Xingyu and Andreoletti, Gaia and Albrecht, Jake and Pellegrino, Robert and Wang, Zehua and Yang, Stephen and Dh́ondt, Robbe and Ghinis, Achilleas and Vranckx, Stijn and Hu, Yue and Chen, Jiacheng and Pan, Liangzhen and Chen, Siyuan and Tang, Jianing and Tang, Jianming and Dong, Menglong and Liu, Yang and Shen, Qian and Yuan, Yuan and Li, Ping and He, Jiazhen and Zhang, Min and Sanchez-Lengeling, Benjamin and Mainland, Joel D. and Gerkin, Richard C. and Meyer, Pablo},
  booktitle = {Proceedings of the National Academy of Sciences (PNAS)},
  volume = {123},
  year = {2026},
  month = aug,
  doi = {10.1073/pnas.2611057123},
  url = {https://doi.org/10.1073/pnas.2611057123},
  preprint = {https://doi.org/10.64898/2025.12.13.694160},
  github = {https://github.com/Satarifard/DREAM-olfactory-mixtures-prediction-challenge},
  keywords = {olfaction, datacentric-ai, mixtures, ai},
  abstract = {Crowdsources predictive models across 26 international teams in the DREAM Olfactory Challenge, demonstrating that compact semantic representations of single odorants generalize to complex mixture perceptual spaces.},
}