{"id":"255bf3e3-7f68-47f2-8672-c0426fc3e2fb","slug":"hf-model-aerosta-rewardhackwatch-1b1etc8-n","name":"rewardhackwatch","description":"Hugging Face model Aerosta/rewardhackwatch. Task: text classification. Library: transformers. 27 downloads. 1 likes.","capabilities":["transformers","safetensors","distilbert","reward-hacking","ai-safety","text-classification","pytorch","misalignment-detection","llm-safety","alignment","en","dataset:custom","arxiv:2511.18397","arxiv:2503.11926","license:mit","model-index","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:55.802Z"}