@article{beyondweblessonsfromscalingsyntheticdata, title = {BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining}, author = { DatologyAI and : and Pratyush Maini and Vineeth Dorna and Parth Doshi and Aldo Carranza and Fan Pan and Jack Urbanek and Paul Burstein and Alex Fang and Alvin Deng and Amro Abbas and Brett Larsen and Cody Blakeney and Charvi Bannur and Christina Baek and Darren Teh and David Schwab and Haakon Mongstad and Haoli Yin and Josh Wills and Kaleigh Mentzer and Luke Merrick and Ricardo Monti and Rishabh Adiga and Siddharth Joshi and Spandan Das and Zhengping Wang and Bogdan Gaza and Ari Morcos and Matthew Leavitt}, year = {2025}, eprint = {2508.10975}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.10975}, }