[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-reliability":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"0de15bee-9ab2-4160-a23e-6d70817e787b","reliability",2,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"3a330546-beae-4173-9b71-9d0d446ff432","llm-judge-reliability-conformal-transitivity-en","How to Trust LLM Judges, Per Input","A diagnostic toolkit shows LLM judges can look stable on average while still being unreliable on individual inputs.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776406194842-ml7e.png","en","2026-04-17T06:09:33.415041+00:00"]