March 2026

arXiv:2603.03475v1 Announce Type: new Abstract: Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B) achieve 61% accuracy through a mixture of reliable and unreliable reasoning pathways: 18.4% of correct predictions employ stable, faithful reasoning while 81.6% emerge through computationally inconsistent pathways. Additionally, 8.8% of all predictions are silent failures — confident yet incorrect outputs. Through comprehensive analysis using novel faithfulness metrics, we […]

Ver mais

arXiv:2603.03470v1 Announce Type: new Abstract: Bisynchronous FIFOs — hardware buffers that mediate data transfer between independent clock domains without a shared global timebase — have been designed, formally verified, and commercially deployed in silicon for over four decades. We survey this literature from Chapiro’s 1984 GALS thesis through Cummings’s Gray-code pointer techniques, Chelcea and Nowick’s mixed-timing interfaces, Greenstreet’s STARI protocol, and the 2015 NVIDIA pausible bisynchronous FIFO, and argue that this body of work constitutes a silicon-proven existence […]

Ver mais

arXiv:2603.03469v1 Announce Type: new Abstract: Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples, with evaluation largely driven by held-out performance and perceived sample quality. In practice, training is often stopped at the minimum of the test loss, taken as an operational indicator of generalization. We challenge this viewpoint by identifying a phase of biased generalization during training, in which the model continues to decrease […]

Ver mais

arXiv:2603.03467v1 Announce Type: new Abstract: Psychotherapy delivery relies on a negotiation between patient self-reports and clinical intuition. Growing evidence for technological support of psychotherapy suggests opportunities to aid the mediation of this tension. To explore this prospect, we designed a prototype of a clinical decision support system (CDSS) for treating veterans with post-traumatic stress disorder in a Prolonged Exposure (PE) therapy intensive outpatient program. We conducted a two-phase interview study to collect perspectives from practicing PE clinicians and […]

Ver mais

arXiv:2603.03464v1 Announce Type: new Abstract: We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this joint energy yields an iterative update interleaving Hopfield retrieval with Laplacian propagation. Memory retrieval provides regime-dependent benefits: up to 2.0~pp on sparse citation networks and up to 5 pp additional robustness under feature masking; the iterative energy-descent architecture itself is a strong inductive bias, with all variants (including the memory-disabled […]

Ver mais

arXiv:2603.03462v1 Announce Type: new Abstract: The Cellular Vehicle-to-Everything (C-V2X), introduced and developed by the 3GPP, is a promising technology for the Autonomous Driving System (ADS). C-V2X aims to fulfill the Service-Level Requirements (SLRs) of ADS to ensure road safety following the development of the latest version, i.e., the NR-V2X. However, vulnerabilities threatening road safety in NR-V2X persist that have yet to be investigated. Existing research primarily evaluates road safety based on successful packet receptions. In this work, we […]

Ver mais

arXiv:2603.03459v1 Announce Type: new Abstract: We investigate when transformer MLP nonlinearity is actually necessary. A gate with $d+1$ parameters decides when to replace the full MLP with a linear surrogate. Through systematic investigation across six models (162M-2.8B parameters), two architectures, and three corpora, we establish that nonlinearity need cannot be predicted from token identity: cross-corpus correlation is zero ($r < 0.05$). The routing decision is fully contextual. Despite weak per-instance predictability, the gate exploits a heavily skewed distribution […]

Ver mais

arXiv:2603.03457v1 Announce Type: new Abstract: Over the last two decades, research funders have adopted Open Access (OA) mandates, with various forms and success. While some funders emphasize gold OA through article processing charges, others favour green OA and repositories, leading to a fragmented policy landscape. Compliance with these mandates depends on several factors, including disciplinary field, monitoring, and availability of repository infrastructure. Based on 5 million papers supported by 36 funders from 20 countries, 11 million papers funded […]

Ver mais

arXiv:2603.03456v1 Announce Type: new Abstract: Agentic coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. Throughout an agent’s lifetime, it must navigate tensions between explicit instructions, learned values, and environmental pressures, often in contexts unseen during training. Prior work on model preferences, agent behavior under value tensions, and goal drift has relied on static, synthetic settings that do not capture the complexity of real-world environments. To this end, we introduce a framework built on OpenCode […]

Ver mais

arXiv:2603.03454v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL algorithms do not provide an efficient way to find a fair compromise. FairDICE (see arXiv:2506.08062v2) seeks to fill this gap by adapting OptiDICE (an offline RL algorithm) to automatically learn weights for multiple objectives to e.g. incentivise fairness among objectives. As […]

Ver mais