{"total":18,"rows":[{"id":"2512.10169","title":"The 2025 Foundation Model Transparency Index","created":"2025-12-11","cited_by_count":11,"area":null},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2602.15210","title":"\\\"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2607.11052","title":"Domain-Aware Scaling Laws Uncover Data Synergy","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2603.08231","title":"Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.22339","title":"Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2604.13286","title":"English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.13225","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.23885","title":"Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25846","title":"On the Limits of Model Merging for Multilinguality in Pre-Training","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.29355","title":"Cross-Lingual Transfer for Machine Translation in Turkic Languages","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.17088","title":"There is No Theoretical Curse of Multilinguality For Embedding Space Structure","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.30535","title":"Feeding BabyLMs Macaroni: Code-Switching Curricula Cause Cross-Lingual Convergence","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.39640","title":"Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40295","title":"How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}