[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-model-as-judge":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"0da5d146-0add-4cbf-bed7-a4647e3cc502","model-as-judge",0,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"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"]