arXiv:2512.00142v1 Announce Type: cross Abstract: This research introduces the Decentralized Finance (DeFi) TrustBoost Framework, which combines blockchain technology and Explainable AI to address challenges faced by lenders underwriting small business loan applications from low-wealth households. The framework is designed with a strong emphasis on fulfilling four crucial requirements of blockchain and AI systems: confidentiality, compliance with data protection laws, resistance to adversarial attacks, and compliance with regulatory audits. It presents a technique for tamper-proof auditing of automated AI decisions and a strategy for on-chain (inside-blockchain) and off-chain data storage to facilitate collaboration within and across financial organizations.

arXiv:2512.00281v1 Announce Type: cross Abstract: Early detection of malignant lung nodules is critical, but its dependence on size and growth in screening inherently delays diagnosis. We present an AI system that redefines lung cancer screening by performing both detection and malignancy diagnosis directly at the nodule level on low-dose CT scans. To address limitations in dataset scale and explainability, we designed an ensemble of shallow deep learning and feature-based specialized models. Trained and evaluated on 25,709 scans with 69,449 annotated nodules, the system outperforms radiologists, Lung-RADS, and leading AI models (Sybil, Brock, Google, Kaggle). It achieves an area under the receiver operating characteristic curve (AUC) of 0.98 internally and 0.945 on an independent cohort. With 0.5 false positives per scan at 99.3\% sensitivity, it addresses key barriers to AI adoption. Critically, it outperforms radiologists across all nodule sizes and stages, excelling in stage 1 cancers, and all growth-based metrics, including the least accurate: Volume-Doubling Time. It also surpasses radiologists by up to one year in diagnosing indeterminate and slow-growing nodules.

arXiv:2512.00350v1 Announce Type: cross Abstract: We introduce MedCondDiff, a diffusion-based framework for multi-organ medical image segmentation that is efficient and anatomically grounded. The model conditions the denoising process on semantic priors extracted by a Pyramid Vision Transformer (PVT) backbone, yielding a semantically guided and lightweight diffusion architecture. This design improves robustness while reducing both inference time and VRAM usage compared to conventional diffusion models. Experiments on multi-organ, multi-modality datasets demonstrate that MedCondDiff delivers competitive performance across anatomical regions and imaging modalities, underscoring the potential of semantically guided diffusion models as an effective class of architectures for medical imaging tasks.

arXiv:2512.00403v1 Announce Type: cross Abstract: Recent work on autonomous scientific discovery has leveraged LLM-based agents to integrate problem specification, experiment planning, and execution into end-to-end systems. However, these frameworks are often confined to narrow application domains, offer limited real-time interaction with researchers, and lack principled mechanisms for determining when to halt exploration, resulting in inefficiencies, reproducibility challenges, and under-utilized human expertise. To address these gaps, we propose \textit{SelfAI}, a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations, a Cognitive Agent powered by LLMs with optimal stopping criteria to iteratively refine hyperparameter searches, and an Experiment Manager responsible for orchestrating parallel, fault-tolerant training workflows across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback. We further introduce two novel evaluation metrics, Score and $\text{AUP}_D$, to quantify discovery efficiency and search diversity. Across regression, NLP, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials compared to classical Bayesian optimization and LLM-based baselines, while enabling seamless interaction with human researchers.

arXiv:2512.00590v1 Announce Type: cross Abstract: Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3$\times$ fewer than AriGraph and $

arXiv:2502.07663v3 Announce Type: replace Abstract: AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes. Through a randomized between-subjects experiment with 233 participants, we examined human susceptibility to such manipulation in financial (e.g., purchases) and emotional (e.g., conflict resolution) decision-making contexts. Participants interacted with one of three AI agents: a neutral agent (NA) optimizing for user benefit without explicit influence, a manipulative agent (MA) designed to covertly influence beliefs and behaviors, or a strategy-enhanced manipulative agent (SEMA) equipped with established psychological tactics, allowing it to select and apply them adaptively during interactions to reach its hidden objectives. By analyzing participants' preference ratings, we found significant susceptibility to AI-driven manipulation. Particularly across both decision-making domains, interacting with the manipulative agents significantly increased the odds of rating hidden incentives higher than optimal options (Financial, MA: OR=5.24, SEMA: OR=7.96; Emotional, MA: OR=5.52, SEMA: OR=5.71) compared to the NA group. Notably, we found no clear evidence that employing psychological strategies (SEMA) was overall more effective than simple manipulative objectives (MA) on our primary outcomes. Hence, AI-driven manipulation could become widespread even without requiring sophisticated tactics and expertise. While our findings are preliminary and derived from hypothetical, low-stakes scenarios, we highlight a critical vulnerability in human-AI interactions, emphasizing the need for ethical safeguards and regulatory frameworks to protect human autonomy.

arXiv:2506.02139v5 Announce Type: replace Abstract: We propose semantic anchoring, a unified account of how large language models turn pretrained capacity into goal-directed behavior: external structure (in-context examples, retrieval, or light tuning) binds the model's latent patterns to desired targets. Unified Contextual Control Theory (UCCT) formalizes this via anchoring strength $S = \rho_d - d_r - \log k$, where $\rho_d$ measures target cohesion in representation space, $d_r$ measures mismatch from prior knowledge, and $k$ is the anchor budget. UCCT predicts threshold-like performance flips and strictly generalizes in-context learning, reading retrieval and fine-tuning as anchoring variants. Three controlled studies provide evidence. Experiment 1 demonstrates cross-domain anchoring rebinding strong priors in text and vision. Experiment 2 varies representational familiarity via numeral bases (base-10/8/9) at fixed complexity, yielding ordered thresholds and transfer patterns tracking $\rho_d$, $d_r$, and $S$. Experiment 3 establishes a geometry-to-behavior correlate: layer-wise peak anchoring and trajectory area predict few-shot thresholds $\theta_{50}$. UCCT offers testable theory and practical metrics for optimizing prompts, retrieval, and tuning.

arXiv:2502.07299v3 Announce Type: replace-cross Abstract: The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-trained models have achieved great success in analyzing these macromolecules individually, their interconnected nature remains underexplored. This paper follows the guidance of the central dogma to redesign both the data and model pipeline and offers a comprehensive framework, Life-Code, that spans different biological functions. As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences. As for the model, we design a codon tokenizer and a hybrid long-sequence architecture to encode the interactions between coding and non-coding regions through masked modeling pre-training. To model the translation and folding process with coding sequences, Life-Code learns protein structures of the corresponding amino acids by knowledge distillation from off-the-shelf protein language models. Such designs enable Life-Code to capture complex interactions within genetic sequences, providing a more comprehensive understanding of multi-omics with the central dogma. Extensive experiments show that Life-Code achieves state-of-the-art results on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.

arXiv:2509.25721v3 Announce Type: replace-cross Abstract: We present an extended version of the AI Productivity Index (APEX-v1-extended), a benchmark for assessing whether frontier models are capable of performing economically valuable tasks in four jobs: investment banking associate, management consultant, big law associate, and primary care physician (MD). This technical report details the extensions to APEX-v1, including an increase in the held-out evaluation set from n = 50 to n = 100 cases per job (n = 400 total) and updates to the grading methodology. We present a new leaderboard, where GPT5 (Thinking = High) remains the top performing model with a score of 67.0%. APEX-v1-extended shows that frontier models still have substantial limitations when performing typical professional tasks. To support further research, we are open sourcing n = 25 non-benchmark example cases per role (n = 100 total) along with our evaluation harness.

arXiv:2511.12796v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) relies on preference modeling to align machine learning systems with human values, yet the popular approach of random pair sampling with Bradley-Terry modeling is statistically limited and inefficient under constrained annotation budgets. In this work, we explore alternative sampling and evaluation strategies for preference inference in RLHF, drawing inspiration from areas such as game theory, statistics, and social choice theory. Our best-performing method, Swiss InfoGain, employs a Swiss tournament system with a proxy mutual-information-gain pairing rule, which significantly outperforms all other methods in constrained annotation budgets while also being more sample-efficient. Even in high-resource settings, we can identify superior alternatives to the Bradley-Terry baseline. Our experiments demonstrate that adaptive, resource-aware strategies reduce redundancy, enhance robustness, and yield statistically significant improvements in preference learning, highlighting the importance of balancing alignment quality with human workload in RLHF pipelines.

Want to stay on top of the science and politics driving biotech today? Sign up to get our biotech newsletter in your inbox.

Good morning. My colleagues will be in Orlando later this week for the American Society of Hematology meeting. Sign up for their newsletter to stay on top of the news from the conference. We’re also holding an event there on Friday.

Fight around hospital drug discount program escalates with new lawsuit

The American Hospital Association and several hospital systems have filed a lawsuit against the Trump administration, seeking to halt an upcoming pilot program for a controversial drug discount program.

Continue to STAT+ to read the full story…

© Adobe

I was moments away from a routine screening colonoscopy when it happened again. The warm and professional pre-procedure nurse began preparing for intravenous insertion. She tied the tourniquet loosely around my arm, took a quick glance, and untied it within seconds. “I can’t find a vein. You must be dehydrated,” she said, moving immediately to the back of my hand.

I paused. I didn’t feel dehydrated. Yes, I had followed the bowel prep instructions, consuming only liquids the day before, but I had no signs of dehydration. I knew my body. I knew my veins.

Read the rest…

© AIZAR RALDES/AFP via Getty Images

npj Digital Medicine, Published online: 01 December 2025; doi:10.1038/s41746-025-02115-x

The role of digital twins in P4 medicine: A paradigm for modern healthcare

Digital health is expected to improve efficiency and quality of health. Health information technologies (HIT) imply allocated time, appropriate training and new types of responsibility whose physical and mental impact on healthcare professionals (HCPs) has emerged as an important issue. The present review provides updated data and opinions about such potential impact and discusses the relevance of ongoing programs established to better characterize barriers and facilitators of HIT implementation. The extent of Internet-based healthcare information and digital apps imposes new responsibilities on HCPs in helping patients select reliable sources and incorporate them in the understanding and self-management of the disease. Several reviews also identified exhaustion, depersonalization, workload, over-alerting, poor work-life integration and job unsatisfaction as potential drivers of electronic health report (EHR)-associated clinician burnout and/or HIT unacceptability. Paradoxically, the increasing use of generative artificial intelligence in the decision-making process may in turn introduce an additional layer of complexity due to required specific skills and associated cognitive overload and stress. Regarding EHRs, various approaches like more proportionate use, better adequation of available commercial tools, or multidisciplinary workflows within the clinic and building of new specialty-specific tools are expected to reduce clinician burden. The ongoing E-health Efficiency Evaluation (E3) project has been developed to define the factors and dimensions impacting overall digital environment and to identify relevant ways of optimizing its acceptability by HCPs. The way of preventing and alleviating the adverse effects of digital health is a major challenge that all HIT stakeholders should be aware of.