{"id":"2603.06594","title":"A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness","url":"https://codeofpaper.com/paper/2603.06594","arxiv_url":"https://arxiv.org/abs/2603.06594","published":"2026-02-04","code":"official","best":{"full_name":"SchwinnL/LLMJudgeReliability","url":"https://github.com/SchwinnL/LLMJudgeReliability","tier":"official","stars":7,"license":"MIT","framework":null,"language":null,"last_commit":"2026-03-11T08:18:29"},"most_starred_community":null,"implementations":[{"full_name":"SchwinnL/LLMJudgeReliability","url":"https://github.com/SchwinnL/LLMJudgeReliability","tier":"official","stars":7,"license":"MIT","framework":null,"language":null,"last_commit":"2026-03-11T08:18:29"}],"possible_matches":0}