Add CC-scale MinerU-HTML layout-clustering + propagation pipeline (91% fewer LLM calls, F1=0.91)#2075
Draft
VibhuJawa wants to merge 118 commits into
Draft
Commits
Commits on Jun 13, 2026
- committed
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- committed
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- andcommitted
Commits on Jun 14, 2026
- andcommitted
- andcommitted
- andcommitted
- committed
- committed
- andcommitted
- committed
- committed
- committed
- committed
- andcommitted
- andcommitted
- andcommitted
- committed
- committed
- committed
- committed
- andcommitted
- committed
- committed
- andcommitted
- andcommitted
- andcommitted
- andcommitted
- committed
- andcommitted
- andcommitted
- andcommitted
- committed
- committed
- andcommitted
- committed
- andcommitted
- committed
- committed
- committed
- andcommitted
- committed
- committed
- committed
- committed
- andcommitted
- andcommitted
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- andcommitted
- andcommitted
- committed
Commits on Jun 15, 2026
Add module docstrings to _base_stages.py and layout_template.py (style alignment with SemanticDedup)
committed- committed
- committed
- committed
- committed