AgentNativeResearchLab/arc-agi3-cc-opus4.8-g50t download history

AgentNativeResearchLab/arc-agi3-cc-opus4.8-g50t is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 829 times (146 in the last 7 days), and 2,282 times in total. It ranks #22,238 among datasets by monthly downloads.

ARC-AGI-3 g50t — Agent Trajectories (cc-opus4.8) Gameplay trajectories from the harness×model pair cc-opus4.8 playing the ARC-AGI-3 game g50t, part of the ARA-as-world-model generalization experiment. The agent builds a structured world model (an Agent-Native Research Artifact) live d

Open AgentNativeResearchLab/arc-agi3-cc-opus4.8-g50t on Hugging Face