DJ-Research/GameBoyWorlds-Playthrough-Contamination-Check download history

DJ-Research/GameBoyWorlds-Playthrough-Contamination-Check is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 105 times (6 in the last 7 days), and 105 times in total. It ranks #109,997 among datasets by monthly downloads.

Documentation Density Predicts Benchmark Performance: A Contamination Probe Using Official and Fan-Made Pokémon Titles Abstract. Benchmark scores on well-documented domains conflate what a model can reason about with what it has memorised. We construct a 400-item short-answer benchmar

Open DJ-Research/GameBoyWorlds-Playthrough-Contamination-Check on Hugging Face

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