arXivHang Zhang, Qihao Ye, Litong Liu, Yunbei Zhang, Yugyung Lee, Yue Zhou, Bowen Liu, Emily First, Cheng Han, Qiao ZhuangThu, Nov 5, 2026, 8:44 AM PST
score 16.9
Benchmark shows why math context matters for AI proof writing
Original: LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation
Source: arxiv.org ↗
Writing ELI5 summary…