[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-prompt-sensitivity":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"99c79538-14f4-47b5-b07e-8f2a9da855a0","prompt sensitivity","prompt-sensitivity",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"50662a29-bae9-4d88-b8d8-3d6a83680646","judge-reliability-harness-stress-tests-llm-judges-en","Judge Reliability Harness Stress-Tests LLM Judges","A harness probes how LLM judges change under formatting, paraphrasing, verbosity, and flipped labels.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778740862456-3f4y.png","en","2026-05-14T06:40:33.380748+00:00"]