arXiv:2604.07428v1 Announce Type: new Abstract: Safety in reinforcement learning (RL) is typically enforced through objective shaping while keeping environment dynamics stationary with respect to observable state-action pairs. Under delayed harm, this can lead to replay: after a washout period, reintroducing the same stimulus under matched observable conditions reproduces a similar harmful cascade. We introduce the Replay Suppression Diagnostic (RSD), a controlled exposure-decay-replay protocol that isolates this failure mode under frozen-policy evaluation. We show that, under stationary observable transition […]

Ver mais

arXiv:2604.15328v1 Announce Type: new Abstract: Virtual reality (VR) is increasingly used across psychology, from research and assessment to counseling, psychological treatment, and psychotherapy, with growing applications for children and adolescents. In these contexts, VR is often treated as a relatively neutral delivery medium. This assumption may be misleading. Most consumer head-mounted displays (HMDs) have been designed primarily for adult anthropometry, including adult interpupillary distance (IPD) ranges. As a result, some children may be excluded from participation or may […]

Ver mais

arXiv:2602.16787v1 Announce Type: new Abstract: Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in their causal reasoning ability. While recent work has demonstrated that labeled counterfactual tasks can be useful benchmarks of LLMs’ causal reasoning, producing such data at the scale required to cover the vast potential space of counterfactuals is limited. In this work, we introduce double counterfactual consistency (DCC), a lightweight inference-time method […]

Ver mais

Foundation models in healthcare have largely adopted self supervised pretraining objectives inherited from natural language processing and computer vision, emphasizing reconstruction and large scale representation learning prior to downstream adaptation. We revisit this paradigm in outcome centric clinical prediction settings and argue that, when high quality supervision is available, direct outcome alignment may provide a stronger inductive bias than generative pretraining. We propose a supervised deep learning framework that explicitly shapes representation geometry by maximizing inter class separation […]

Ver mais

Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure. We present IntSeqBERT, a dual-stream Transformer encoder for masked integer-sequence modelling on OEIS. Each sequence element is encoded along two complementary axes: a continuous log-scale magnitude embedding and sin/cos modulo embeddings for 100 residues (moduli $2$–$101$), fused via FiLM. Three prediction heads (magnitude regression, sign classification, […]

Ver mais

Burnout is usually discussed as a management issue, a staffing issue, or a culture issue. In workforce-heavy industries, it can also be a software issue. When enterprise systems are slow, fragmented, confusing, or unreliable, the pressure does not stay inside the technology organization. It moves directly to managers, supervisors, support teams, and frontline employees. People spend more time double-checking information, chasing missing data, correcting errors, and working around tools that were supposed to help them. Anil Kumar Karumuru, […]

Ver mais

How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## AI GTM Strategy: Why AEO Is Replacing Traditional Search By @lomitpatel [ 5 Min read ] AI GTM strategy is shifting from SEO to AEO. Learn how creator-led trust and AI visibility drive growth in the era of answer engines. Read More. The 5 […]

Ver mais

arXiv:2508.11847v3 Announce Type: replace Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems — variants of a Bradley–Terry model — to dropping a worst-case very small fraction of preference data. Our approach is computationally fast and easy to adopt. When we apply our method to matchups from popular LLM ranking platforms, including Chatbot Arena and derivatives, we find that the rankings of top-performing models can be remarkably sensitive to the removal of […]

Ver mais

arXiv:2512.08179v2 Announce Type: replace-cross Abstract: We study estimation of the conditional law $P(Y|X=x)$ and continuous functionals $Psi(P(Y|X=x))$ when $Y$ takes values in a locally compact Polish space, $X in mathbb{R}^p$, and the observations arise from a complex survey design. We propose a survey-calibrated distributional random forest (SDRF) that incorporates complex-design features via a pseudo-population bootstrap, PSU-level honesty, and a Maximum Mean Discrepancy (MMD) split criterion computed from kernel mean embeddings of H'{a}jek-type (design-weighted) node distributions. We provide a […]

Ver mais

Release: datasette-files 0.1a2 The most interesting alpha of datasette-files yet, a new plugin which adds the ability to upload files directly into a Datasette instance. Here are the release notes in full: Columns are now configured using the new column_types system from Datasette 1.0a26. #8 New file_actions plugin hook, plus ability to import an uploaded CSV/TSV file to a table. #10 UI for uploading multiple files at once via the new documented JSON upload API. #11 Thumbnails are […]

Ver mais