@article{usingscalinglawsfordatasourceutilityesti, title = {Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training}, author = {Oleksiy Ostapenko and Charles Guille-Escuret and Luke Kumar and Max Tian and Denis Kocetkov and Gopeshh Subbaraj and Raymond Li and Joel Lamy-Poirier and Sebastien Paquet and Torsten Scholak}, year = {2025}, eprint = {2507.22250}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.22250}, }