In the early days of distributed systems, we lived in a world of Request-Response. One service asked, another answered. It was synchronous, predictable, and easy to trace. But as our systems scaled from a handful of servers to hundreds of microservices, this “web of calls” began to tangle. Today, architects face a fundamental choice when designing how these services talk to one another: Do we use Orchestration (the Conductor approach) or Choreography (the Dance approach)? This choice isn’t […]

Ver mais

arXiv:2601.08891v1 Announce Type: new Abstract: Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers, limiting trust and explainability. This paper presents Explanation-Guided Training (EGT), a multi-objective framework that improves interpretability and consistency in early-exit networks through attention-based regularization. EGT introduces an attention consistency loss that aligns early-exit attention maps with the final exit. The framework jointly optimizes […]

Ver mais

arXiv:2601.20882v1 Announce Type: new Abstract: Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents’ capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps cycle in real-world software, including developing, deploying, and managing, requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions. However, existing benchmarks focus on isolated problems and lack environments and tool interfaces for DevOps. We introduce […]

Ver mais

Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app’s predictions? We address this question by embedding performative predictions […]

Ver mais

Release: datasette-ports 0.1 Another example of README-driven development, this time solving a problem that might be unique to me. I often find myself running a bunch of different Datasette instances with different databases and different in-development plugins, spreads across dozens of different terminal windows – enough that I frequently lose them! Now I can run this: datasette install datasette-ports datasette ports And get a list of every running instance that looks something like this: http://127.0.0.1:8333/ – v1.0a26 Databases: […]

Ver mais

arXiv:2602.06883v1 Announce Type: cross Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper, we analyze the ability of vision transformer components to adapt their outputs to changes in inputs, or, in other words, their plasticity. Defined as an average rate of change, it captures the sensitivity to input perturbation; in particular, a high plasticity […]

Ver mais

arXiv:2602.03854v1 Announce Type: new Abstract: Autonomous vehicles (AVs) are emerging as a transformative innovation in transportation, offering potential benefits in safety, sustainability, and efficiency. Saudi Arabian adoption of AVs aligns with Vision 2030, emphasizing smart mobility through initiatives such as the Riyadh Autonomous Metro and self-driving cars. This study explores Saudi citizens perceptions of AVs before and after exposure to these technologies and examines whether demographic factors age, gender, education level, and driving habits affect acceptance. Using quantitative […]

Ver mais