The learning rate is 2e-5 with 100% warm up and a batch size of 32.

The red font indicates content that should not be extracted or does not match the original text.

Therefore, our labels may contain errors. Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)? If it links to or relies on external resources, a) are there guarantees that they will exist, and remain constant, over time; b) are there official archival versions of the complete dataset (i.e., including the external resources as they existed at the time the dataset was created); c) are there any restrictions (e.g., licenses, fees) associated with any of the external resources that might apply to a future user? Please provide descriptions of all external resources and any restrictions associated with them, as well as links or other access points, as appropriate.

Unqualified images are removed as described in Appendix A.3. Was the "raw" data saved in addition to the preprocessed/cleaned/labeled data (e.g., to

Wisdom has been laying eggs since the Eisenhower Administration. Breakthroughs, discoveries, and DIY tips sent every weekday. One of the world's most famous birds has returned to her nesting site. Wisdom, the 75-year-old albatross is known as the world's oldest breeding bird . Earlier this month, she returned to Midway Atoll National Wildlife Refuge in the central Pacific Ocean for the 2025-2026 nesting season.

Agent-Based Models (ABMs) are powerful tools for studying emergent properties in complex systems. In ABMs, agent behaviors are governed by local interactions and stochastic rules. However, these rules are, in general, non-differentiable, limiting the use of gradient-based methods for optimization, and thus integration with real-world data. We propose a novel framework to learn a differentiable surrogate of any ABM by observing its generated data. Our method combines diffusion models to capture behavioral stochasticity and graph neural networks to model agent interactions. Distinct from prior surrogate approaches, our method introduces a fundamental shift: rather than approximating system-level outputs, it models individual agent behavior directly, preserving the decentralized, bottom-up dynamics that define ABMs. We validate our approach on two ABMs (Schelling's segregation model and a Predator-Prey ecosystem) showing that it replicates individual-level patterns and accurately forecasts emergent dynamics beyond training. Our results demonstrate the potential of combining diffusion models and graph learning for data-driven ABM simulation.

Embodied AI agents exploit reward signal flaws through reward hacking, achieving high proxy scores while failing true objectives. We introduce Mechanistically Interpretable Task Decomposition (MITD), a hierarchical transformer architecture with Planner, Coordinator, and Executor modules that detects and mitigates reward hacking. MITD decomposes tasks into interpretable subtasks while generating diagnostic visualizations including Attention Waterfall Diagrams and Neural Pathway Flow Charts. Experiments on 1,000 HH-RLHF samples reveal that decomposition depths of 12 to 25 steps reduce reward hacking frequency by 34 percent across four failure modes. We present new paradigms showing that mechanistically grounded decomposition offers a more effective way to detect reward hacking than post-hoc behavioral monitoring.

The original questions are in bold . The subtext to each question is in italics. The answers are in plain text with no formatting. The questions in this section are primarily intended to encourage dataset creators to clearly articulate their reasons for creating the dataset and to promote transparency about funding interests. For what purpose was the dataset created? Was there a specific task in mind? Was there a specific gap that needed to be filled? The Dollar Street dataset is a supervised image dataset derived from Gapminder's Dollar Street project ( https://www.gapminder.org/dollar-street) that contains everyday household items from homes around the world. It was created with three goals in mind: 1. Make available a highly curated set of images with valuable metadata (e.g. Our evaluation results show that the Dollar Street dataset can add significant value to accuracy improvements when considering computer vision images that represent the geographic and socioeconomic diversity of the world. Concretely, this means that the dataset only contains CC-BY-licensed works.

The loss is computed for this mini-batch and then the parameters of the neural network are updated via stochastic gradient descent. UMAP: First, since automatic differentiation is used, not only the head of a negative sample edge is repelled from the tail but both repel each other. Second, the same number of edges are sampled in each epoch. This leads to a different repulsive weight for Parametric UMAP as described in Theorem A.1. Parametric UMAP's negative sampling is uniform from a batch that is itself sampled Since UMAP's implementation considers a point its first nearest neighbor, but the C Computing the expected gradient of UMAP's optimization procedure In this appendix, we show that the expected update in UMAP's optimization scheme does not It is continuously differentiable unless two embedding points coincide.