@article{bhashakritikabuildingsyntheticpretrainin, title = {BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages}, author = {Guduru Manoj and Neel Prabhanjan Rachamalla and Ashish Kulkarni and Gautam Rajeev and Jay Piplodiya and Arul Menezes and Shaharukh Khan and Souvik Rana and Manya Sah and Chandra Khatri and Shubham Agarwal}, year = {2025}, eprint = {2511.10338}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.10338}, }