This Letter describes a search for narrowly resonant new physics using a machine-learning anomaly detection procedure that does not rely on a signal simulations for developing the analysis selection. Weakly supervised learning is used to train classifiers directly on data to enhance potential signals. The targeted topology is dijet events and the features used for machine learning are the masses of the two jets. The resulting analysis is essentially a three-dimensional search $A\to BC$, for $m_A\sim 𝒪(\mathrm{\text{TeV}})$, $m_B,m_C\sim 𝒪(100\mathrm{\text{GeV}})$ and $B,C$ are reconstructed as large-radius jets, without paying a penalty associated with a large trials factor in the scan of the masses of the two jets. The full Run 2 $\sqrt{s}=13$ TeV $pp$ collision data set of 139 fb${}^{-1}$ recorded by the ATLAS detector at the Large Hadron Collider is used for the search. There is no significant evidence of a localized excess in the dijet invariant mass spectrum between 1.8 and 8.2 TeV. Cross-section limits for narrow-width $A$, $B$, and $C$ particles vary with $m_A$, $m_B$, and $m_C$. For example, when $m_A=3$ TeV and $m_B\gtrsim 200$ GeV, a production cross section between 1 and 5 fb is excluded at 95% confidence level, depending on $m_C$. For certain masses, these limits are up to 10 times more sensitive than those obtained by the inclusive dijet search. These results are complementary to the dedicated searches for the case that $B$ and $C$ are Standard Model bosons.

中文翻译：

---

使用ATLAS探测器中的13TeVpp碰撞在弱监督下进行Dijet共振搜索

这封信描述了使用机器学习异常检测程序寻求狭义共振新物理学的方法，该程序不依赖信号模拟来进行分析选择。弱监督学习用于直接在数据上训练分类器，以增强潜在信号。目标拓扑是双喷射事件，用于机器学习的特征是两个喷射的质量。结果分析本质上是三维搜索$\mathrm{一种}\to 乙C$，对于 ${米}_{\mathrm{一种}}〜𝒪（\mathrm{\text{电视}}）$， ${米}_{乙}，{米}_C〜𝒪（100\mathrm{\text{GeV}}）$ 和 $乙，C$它们被重建为大半径射流，而在扫描这两个射流的质量时无需付出与较大试验因素相关的罚款。完整版2$\sqrt{s}=13$ 电视 $pp$ 139 fb的碰撞数据集${}^{-\mathrm{1个}}$大型强子对撞机的ATLAS探测器记录的数据用于搜索。没有明显的证据表明双喷射不变质谱在1.8和8.2 TeV之间存在局部过量。窄宽度的横截面限制$\mathrm{一种}$， $乙$和 $C$ 颗粒随 ${米}_{\mathrm{一种}}$， ${米}_{乙}$和 ${米}_C$。例如，当${米}_{\mathrm{一种}}=3$ TeV和 ${米}_{乙}\gtrsim 200$ GeV，在1至5 fb之间的生产横截面，在95％置信水平下被排除，具体取决于 ${米}_C$。对于某些质量，这些限制比包含性双射流搜索获得的限制高多达10倍。这些结果是对以下情况的专门搜索的补充：$乙$ 和 $C$ 是标准模型玻色子。