{"id":"2604.28075","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","url":"https://codeofpaper.com/paper/2604.28075","arxiv_url":"https://arxiv.org/abs/2604.28075","published":"2026-04-30","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}