Abstract: An array substrate (100) and a display device. The array substrate (100) includes a bonding area (102). The array substrate (100) includes a substrate (10), a first conductive layer (20) on the substrate (10), a first insulating layer (30) on one side of the first conductive layer (20) away from the substrate (10), and a second conductive layer (40) on one side of the first insulating layer (30) away from the substrate (10). The bonding area (102) is provided with bonding pins (201), and the bonding pin (201) includes a first conductive portion (21) and a second conductive portion (41) located on the side of the first conductive portion (21) away from the substrate (10), the first conductive portion (21) is located in the first conductive layer (20), the second conductive portion (41) is located in the second conductive layer (40), and the first conductive portion (21) is in direct contact with the second conductive portion (41).

Abstract: A fluidized solidified soil based on gold tailings includes the following raw materials in parts by mass: 75 parts to 80 parts of gold tailings, 5.2 parts to 13 parts of a dispersant solution, and 9 parts to 16 parts of a solidifying material. A preparation method includes the following steps: mixing the gold tailings with the dispersant solution, and then stirring to obtain a suspension slurry of the gold tailings; and adding the solidifying material, and stirring to obtain the fluidized solidified soil. In the present disclosure, the gold tailings are used as a main material, combined with a special dispersant solution and a special solidifying material, and a fluidized solidified soil is prepared with fluidity suitable for pumping and a certain strength after hardening. The fluidized solidified soil prevents the pollution caused by gold tailings landfilling, and can be used as a filling material for various construction projects.

Abstract: Technologies for monitoring input feature health for machine learning models and detecting anomalies are described. Embodiments include receiving, by a trained machine learning model and from an online system, a set of historical values and a current feature value of a time series feature, the time series feature represents one or more measured values of the online system. Embodiments include predicting an expected feature value and an expected range of values using the set of historical values. Embodiments include receiving the expected feature value and the expected range of values. Embodiments include receiving the current feature value. Embodiments include determining that an anomaly condition is present based on the current feature value, the expected feature value, and the expected range of values. Embodiments include generating an alert for the anomaly condition that includes the severity metric and the duration metric.