PaulR11/training-runs-intragroup-fp download history

PaulR11/training-runs-intragroup-fp is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 38 times (12 in the last 7 days), and 5,631 times in total. It ranks #227,732 among datasets by monthly downloads.

GRPO Training Runs — Intragroup Pairwise + FP Calibration (Single-Target) Part of the data release for "Training Alignment Auditors via Reinforcement Learning" (ICLR 2026). Three single-target GRPO runs using the PV2 intragroup pairwise reward (Petri-informed within-group C(8,2)=28 compar

Open PaulR11/training-runs-intragroup-fp on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.