{"id":"2604.18418","title":"MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline","url":"https://codeofpaper.com/paper/2604.18418","arxiv_url":"https://arxiv.org/abs/2604.18418","published":"2026-04-20","code":"official","best":{"full_name":"uni-medical/MedProbeBench","url":"https://github.com/uni-medical/MedProbeBench","tier":"official","stars":13,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-04-21T04:04:17"},"most_starred_community":null,"implementations":[{"full_name":"uni-medical/MedProbeBench","url":"https://github.com/uni-medical/MedProbeBench","tier":"official","stars":13,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-04-21T04:04:17"}],"possible_matches":0}