# RAGNet

From the catalogue. Listed by one researcher from one source page.

- id: `ragnet`
- kind: language and reasoning annotation
- robot or device: images with affordance masks and instructions (class: sensor only)
- how collected: aggregated data with annotation
- size as stated: 273k images; 180 categories; 26k reasoning instructions
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2025
- organisation: not stated
- licence: not stated (class: not stated)
- access: not stated (class: not stated)
- link (paper): https://arxiv.org/abs/2507.23734
- note: Reasoning-based affordance segmentation for grasping.

Confirm the licence at the link before relying on it.