{"type":"post","id":"accepted-but-wrong-typical-input-gates-release-41-75c83c","slug":"accepted-but-wrong-typical-input-gates-release-41-75c83c","title":"Accepted but Wrong: typical-input gates release 41% of wrong LLM API-migration repairs","description":"A preregistered study of 73 API and runtime migration tasks found that ordinary tests on typical inputs released 41% of incorrect LLM repairs.","retrieval_nugget":"A preregistered study of 73 API and runtime migration tasks found that ordinary tests on typical inputs released 41% of incorrect LLM repairs.","published_at":"2026-11-07","updated_at":"2026-11-07","record_date":"2026-11-07","date_kind":"published_at","topics":["verification","coding-agents"],"entities":["Xiaobo Chen","Genliang Zhu","Ziyuan Wang","Chu Wang","CPython","Node.js","SQLite","GPT-5.6-luna"],"related_patterns":["verification-bandwidth-is-the-scarce-resource"],"novelty_label":"new_angle","what_changed":"The study shifts attention from general code-review correctness to silent semantic failures in LLM-written API-migration repairs that pass typical-input tests.","prior_refs":["https://newruntime.com/posts/a-separate-public-benchmark-analysis-evaluated-23-models-6f6beb/"],"source_url":"https://arxiv.org/abs/2611.08269","source_urls":["https://arxiv.org/abs/2611.08269"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:accepted-but-wrong-typical-input-gates-release-41-75c83c","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/accepted-but-wrong-typical-input-gates-release-41-75c83c/","markdown":"https://newruntime.com/posts/accepted-but-wrong-typical-input-gates-release-41-75c83c.md","json":"https://newruntime.com/posts/accepted-but-wrong-typical-input-gates-release-41-75c83c.json"},"markdown_url":"https://newruntime.com/posts/accepted-but-wrong-typical-input-gates-release-41-75c83c.md","next_reads":[{"type":"topic","path":"/topics/verification/","url":"https://newruntime.com/topics/verification/","title":"Verification","reason":"Explore the verification topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/verification.md","json_url":"https://newruntime.com/topics/verification.json"},{"type":"topic","path":"/topics/coding-agents/","url":"https://newruntime.com/topics/coding-agents/","title":"Coding Agents","reason":"Explore the coding-agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/coding-agents.md","json_url":"https://newruntime.com/topics/coding-agents.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}