Philly's'transit vigilante' created a real-time bus tracker for his neighbors With a sports timer and some clever coding, Max Goldberg built a DIY display that tells South Philly commuters exactly when their next bus will arrive. Breakthroughs, discoveries, and DIY tips sent every weekday. Philadelphia's mass transit system has had a rough go of it lately. The Pennsylvania city's main public transit provider, SEPTA, has been dealing with massive service cuts, including the elimination of entire bus routes. But South Philly resident Max Goldberg is undeterred.

Commonsense question answering is a crucial task that requires machines to employ reasoning according to commonsense. Previous studies predominantly employ an extracting-and-modeling paradigm to harness the information in KG, which first extracts relevant subgraphs based on pre-defined rules and then proceeds to design various strategies aiming to improve the representations and fusion of the extracted structural knowledge. Despite their effectiveness, there are still two challenges. On one hand, subgraphs extracted by rule-based methods may have the potential to overlook critical nodes and result in uncontrollable subgraph size. On the other hand, the misalignment between graph and text modalities undermines the effectiveness of knowledge fusion, ultimately impacting the task performance. To deal with the problems above, we propose a novel framework: \textbf{S}ubgraph R\textbf{E}trieval Enhanced by Gra\textbf{P}h-\textbf{T}ext \textbf{A}lignment, named \textbf{SEPTA}. Firstly, we transform the knowledge graph into a database of subgraph vectors and propose a BFS-style subgraph sampling strategy to avoid information loss, leveraging the analogy between BFS and the message-passing mechanism. In addition, we propose a bidirectional contrastive learning approach for graph-text alignment, which effectively enhances both subgraph retrieval and knowledge fusion. Finally, all the retrieved information is combined for reasoning in the prediction module. Extensive experiments on five datasets demonstrate the effectiveness and robustness of our framework.

SEPTA will soon begin using an artificial intelligence system that can detect people getting on trains and buses with guns. Why it matters: There's been a dramatic spike in violent crime aboard the public transit system. Driving the news: SEPTA is the U.S.'s first major transit system to test out the AI technology, known as ZeroEyes. It's been deployed by the Pentagon as well as public schools, universities and Fortune 500 companies in more than 30 states, according to a SEPTA statement. How it works: The company behind ZeroEyes was founded by former Navy SEALs who used hundreds of thousands of images and videos to train the AI system.