AI 编码智能体复现 CMS 的 prompt J/psi 截面测量
AI-Assisted Analysis of CMS Open Data: Prompt J/psi Cross-Section Measurements in pp and Peripheral PbPb Collisions at sqrt(S)= 7 TeV and sqrt(sNN) = 2.76 TeV
OpenAI Codex 在物理学家监督下,用 CMS 公开数据把 J/psi 截面几乎完整复测了一遍,pp 结果比值均值正好 1.000。做科研数据分析的人可以看看它的具体工作流和失败模式,这可能是智能体做严肃科学分析的一次实践样本。
一项研究测试了 OpenAI Codex 在人工监督下,基于 CMS Open Data 独立完成对撞机物理分析的能力。
智能体完成了双μ子事例筛选、二维不变质量与衰减长度拟合、蒙特卡洛探测器模拟以及系统误差评估,并使用自定义全探测器模拟确定接收度与重建效率。在 sqrt(s) = 7 TeV 的 pp 对撞中,复测的 prompt J/psi 微分截面与 CMS 已发表结果的比值均值为 1.
000、RMS 为 0.215(39 个 bin);
在 sqrt(s_NN) = 2.76 TeV 的 50-100% 边缘 PbPb 对撞中,6 个区间的比值均值为 1.
158、RMS 为 0.225。
研究还梳理了智能体的失败模式,强调结构化人工审查是结果可靠的关键。
AI-Assisted Analysis of CMS Open Data: Prompt J/psi Cross-Section Measurements in pp and Peripheral PbPb Collisions at sqrt(S)= 7 TeV and sqrt(sNN) = 2.76 TeV
We investigate the use of an artificial-intelligence (AI) coding agent, supervised by human physicists, for collider physics analyses using CMS Open Data. OpenAI Codex performs dimuon event selection, two-dimensional invariant-mass and decay-length fits, Monte Carlo detector simulations, and systematic uncertainty evaluation after acquiring physics and experimental knowledge from published studies and external references, with human review at each stage. The workflow is tested on two CMS datasets, with custom full-detector simulations used to determine acceptance and reconstruction efficiencies. In proton-proton collisions at sqrt(s) = 7 TeV, prompt J/psi differential cross sections are measured versus transverse momentum and rapidity. The ratios of remeasured to published CMS cross sections have a mean of 1.000 and an RMS spread of 0.215 across 39 bins. In peripheral (50-100% centrality) PbPb collisions at sqrt(s_NN) = 2.76 TeV, the corresponding prompt J/psi fiducial cross-section ratios have a mean of 1.158 and an RMS spread of 0.225 across six intervals. We identify agent failure modes and demonstrate the importance of structured human review in ensuring reliable results.
本条情报归属 AITOP「论文」核心栏目,重点聚焦欧洲人工智能治理与技术生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:OpenAI Codex、CMS、粒子物理、数据分析,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始信息发布自一手权威信源「arXiv: OpenAI」(Tier-1 一手发布),具备高确定性参考价值。截至目前,全网已有 11 家独立信源对该事件进行交叉印证与跟进报道(含 Tibor Blaho、Scale AI、Databricks 等),属于近期高关注度行业信号。