Background Traditional Chinese Medicine (TCM) rheumatology presents unique challenges for AI-assisted clinical decision support, as the diagnostic process relies heavily on tacit knowledge and individualized reasoning. While Large Language Models (LLMs) have shown promise in medical applications, they remain limited by hallucination risks and inability to replicate expert TCM reasoning. Retrieval-Augmented Generation (RAG) offers a potential solution, yet its application to complex TCM dialectical reasoning remains underexplored. Methods We developed TCM-CoT-RAG, a hybrid framework combining RAG with Chain-of-Thought (CoT) prompting, grounded in 1,700 expert-curated clinical cases (1,600 for RAG retrieval; 100 for evaluation, including 50 for blinded expert review by three senior TCM rheumatologists). Deployed on Alibaba Cloud, the five system leverages state-of-the-art LLMs (DeepSeek-V3, Qwen3-235B) under a human-in-the-loop paradigm. We designed a dual-tier evaluation: (1) Objective extraction tasks (Task 1–2) quantified using F1-scores; (2) Generative tasks (Task 3–5) assessed using BERTScore. Two senior TCM rheumatologists (≥15 years clinical experience) blindly assessed model outputs, and a senior chief expert quantified consistency between model predictions and ground truth (GT). Comprehensive ablation studies (S1-S4, S-Skip) isolated the contributions of each CoT module. Results TCM-CoT-RAG substantially improved diagnostic accuracy across five LLMs. DeepSeek-V3 with full-chain CoT-RAG achieved Entity F1 of 44.89% (+16.45% over baseline) and Formula F1 of 32.13% (+8.74% over baseline), with BERTScore of 0.81 indicating strong semantic alignment with expert reasoning. Ablation confirmed that the complete CoT pipeline was essential—removing any reasoning module caused performance collapse below the zero-shot baseline. Two independent experts validated clinical utility (Cohen’s κ > 0.7). DeepSeek-V3 achieved the highest ground-truth consistency at 81.6%, and consistency metrics were quantified by the third expert holding the most senior professional title. Conclusion This proof-of-concept framework demonstrates the potential of RAG-enhanced CoT reasoning to improve diagnostic consistency in TCM, objectifying the Symptom-Diagnosis-Prescription pipeline. It is important to note that this system is designed as an AI-assisted clinical decision-support tool. All recommendations require validation by qualified TCM practitioners before clinical application.
Abstract Software requirement documents—natural-language specifications that define a system’s entities, rules, processes, and interfaces—remain the core knowledge artifact in enterprise software development. Yet they remain inaccessible to automated tooling: downstream tasks like test generation, code scaffolding, compliance checking, and AI-assisted development cannot directly process unstructured prose. We present DKSE (Domain Knowledge Structuring Engine), a tool that automatically converts requirement documents into machine-readable structured ontologies organized around six core asset types: entities, relations, rules, processes, APIs, and dictionaries. DKSE uses an LLM-guided extraction pipeline that accepts multi-format inputs (DOCX, PDF, HTML), outputs YAML-encoded ontologies with full provenance tracing back to source sections, and includes built-in quality assurance tooling for validation, version diffing, and probe generation. In a case study across four banking sub-domains, we ran DKSE on six requirement documents totaling roughly 800,000 Chinese characters. It extracted 3,439 structured assets: 215 entities, 1,227 rules, 739 relations, 182 processes, 482 dictionaries, and 594 APIs. Expert review confirmed full functional-module coverage, with 96% of a stratified sample rated fully accurate and zero hallucinated assets. We validate DKSE’s practical value through three downstream use cases: automated benchmark generation (1,214 machine-graded probes), domain-specific LLM training corpus construction, and knowledge graph ingestion for retrieval-augmented generation. DKSE is built in Rust (~8,000 lines of code) and shipped as a CLI tool with an accompanying web interface. We position this work as a proof-of-concept within a single industry (Chinese banking), not a general-purpose validation. Quantitative evaluation across additional domains, languages, and against baseline extraction methods is left for future work.
Transaction processing systems underpin modern commerce, finance, critical infrastructure, and emerging Self-Sovereign Digital Identity (SSDI) protocols, yet their security has never been studied holistically across the full evolutionary arc of these systems. Over five decades, transaction processing has progressed through four distinct generations, from centralized databases, to distributed databases, to blockchain and distributed ledger technologies (DLTs), and most recently to multi-context systems that span cyber-physical components under real-time constraints. Each generation has introduced new transaction types and, with them, new classes of vulnerabilities; successful exploits now cause billions of dollars in annual losses. Despite this, security research remains fragmented by domain, and the foundational ACID transaction model has not been revisited to reflect the demands of contemporary systems.
Cross-chain technology is the key to solving the “data silo” problem in medical blockchain systems. However, it is difficult for existing cross-chain consensus mechanisms to meet the high standards of data security and consensus efficiency in medical scenarios. Therefore, this paper proposes a medical cross-chain Delegated proof of stake consensus(DPoS) scheme that integrates reputation and contribution evaluation. First, a dynamic reputation evaluation model was constructed, and the historical behaviour and communication quality of nodes were incorporated into the evaluation system, thereby mitigating the risk of centralization caused by the excessive reliance on the number of coins held in the DPoS consensus. Second, a hybrid random block generation mechanism combining the multiparty coin-tossing protocol and the secure shuffling algorithm was proposed. By collaboratively generating a verifiable global random seed and uniformly and randomly shuffling the candidate node sequence, the predictability of the block generation order was eliminated. Finally, a two-layer incentive architecture based on the Shapley value was proposed. Fine-grained contribution assessment mechanisms were established at both the candidate node layer and the voting node layer, making the reward distribution more equitable, enhancing the enthusiasm of nodes for voting and improving the consensus efficiency. Theoretical analysis and experimental results show that compared with the DPoS scheme, the proposed scheme improves the throughput by approximately 30% and reduces the average latency by approximately 50%. Compared with existing similar schemes, this scheme also has significant advantages in terms of reputation calculation overhead and malicious node elimination and can provide efficient and reliable consensus support for cross-chain scenarios in the medical field.
Ana-Maria Istrate, Fausto Milletarì, Fabrizio Castrotorres, Jakub M. Tomczak · 7 authors
Abstract Reasoning models are typically trained against verification mechanisms in formally specified systems such as code or symbolic math. In open domains like biology, however, we lack exact rules to enable large-scale formal verification and instead often rely on lab experiments to test predictions. Such experiments are slow, costly, and cannot scale with computation. In this work, we show that world models of biology or other prior knowledge can serve as approximate oracles for soft verification , allowing reasoning systems to be trained without additional experimental data. We present two paradigms of training models with approximate verifiers: RLEMF : reinforcement learning with experimental model feedback and RLPK : reinforcement learning from prior knowledge. Using these paradigms, we introduce rbio1 , a reasoning model for biology post-trained from a pretrained LLM with reinforcement learning, using learned biological models for verification during training. We demonstrate that soft verification can distill biological world models into rbio1 , enabling it to achieve state-of-the-art performance on perturbation prediction in the PerturbQA benchmark. We further show that composing multiple AI-verifiers improves performance and that models trained with soft biological rewards transfer zero-shot to cross-domain tasks such as disease-state prediction. We present rbio1 as a proof of concept that predictions from biological models can train powerful reasoning systems using simulations rather than experimental data, offering a new paradigm for model training.
Marielle S. Gross, Ananya Dewan, Mario Macis, Eve Budd · 9 authors
Introduction Organoids are living, patient-derived tumor models that are revolutionizing precision medicine and drug development, however current privacy practices strip identifiers, thereby undermining ethics, efficiency, and effectiveness for patients and research enterprises alike. Decentralized biobanking “de-bi” applies non-fungible tokens (NFTs) to empower privacy-preserving specimen tracking and data sharing for networks of scientists, donors, and physicians. We design, develop, and demonstrate a functional de-bi platform for a real-world organoid biobank. Methods Ethnography of the organoid biobanking ecosystem was performed in 2022–2023, with site visits, interviews, focus groups, and structured observations of stakeholder interactions. An initial ERC-721 prototype was developed and tested, informing the design of a comprehensive NFT model. Web and mobile app prototypes were developed with a suite of ERC-1155 protocols representing ecosystem constituents as NFTs. We demonstrated the platform with publicly available Human Cancer Models Initiatives organoids to establish proof-of-concept for decentralized biobanking as the foundation of a democratized biomedical metaverse, or “biomediverse.” Results Scientists revealed key challenges for organoid research and development under policy, scientific, and economic constraints of the life science landscape. We advanced decentralized biobanking as a blockchain overlay network solution with potential to overcome barriers, enhance utility and unlock value by uniting collaborators in a privacy-preserving biomediverse. Dedicated smart contracts created “soulbound” NFTs as de-identified digital twins of patients, physicians, and scientists in a networked organoid ecosystem. We modeled biospecimen collection, processing, and distribution, including generation and expansion of organoids, via an auditable on-chain mechanism. Key features included the ability to bootstrap the digital twin NFT model onto an established organoid biobank, visibility of patient-linked biospecimens and related research activities for all ecosystem participants, as well as tooling for multisided data exchange. Implementing de-bi with ERC-1155 showed potential to minimize gas costs of on-chain activity vs ERC-721, though complementary layer-2 solutions will be essential for economic viability. Conclusion Decentralized biobanking has the potential to enhance efficiency, increase translational impact and drive research discovery through implementation of NFT digital twins for organoid research networks. Importantly, this approach also bolsters ethical practices by fostering inclusion, ensuring transparency, and enhancing accountability across the research ecosystem. Next steps include live pilot testing, market design research to align stakeholder incentives, and technical solutions to support a sustainable, scalable and mutually rewarding biomediverse.
The rapid growth of memecoins within the Web3 ecosystem, driven by platforms like Pump.fun, has made it easier for anyone to create tokens. However, this democratization has also led to an explosion of low-quality or bot-generated projects, often motivated by short-term financial gain. This overwhelming influx of speculative tokens creates a challenge in distinguishing viable memecoins from those that are unlikely to succeed. To address this issue, we introduce CoinVibe, a comprehensive multimodal dataset designed to evaluate the viability of memecoins. CoinVibe integrates textual descriptions, visual content (logos), and community data (user comments, timestamps, and number of likes) to provide a holistic view of a memecoin's potential. In addition, we present CoinCLIP, a novel framework that leverages the Contrastive Language-Image Pre-Training (CLIP) model, augmented with lightweight modules and community data integration, to improve classification accuracy. By combining visual and textual representations with community insights, CoinCLIP provides a robust, data-driven approach to filter out low-quality or bot-driven projects. This research aims to help creators and investors identify high-potential memecoins, while also offering valuable insights into the factors that contribute to their long-term success. The code and dataset are publicly available at https://github.com/hwlongCUHK/CoinCLIP.git.
In Ethereum, the ledger exchanges messages along an underlying Peer-to-Peer (P2P) network to reach consistency. Understanding the underlying network topology of Ethereum is crucial for network optimization, security and scalability. However, the accurate discovery of Ethereum network topology is non-trivial due to its deliberately designed security mechanism. Consequently, existing measuring schemes cannot accurately infer the Ethereum network topology with a low cost. To address this challenge, we propose the Distributed Ethereum Network Analyzer (DEthna) tool, which can accurately and efficiently measure the Ethereum network topology. In DEthna, a novel parallel measurement model is proposed that can generate marked transactions to infer link connections based on the transaction replacement and propagation mechanism in Ethereum. Moreover, a workload offloading scheme is designed so that DEthna can be deployed on multiple distributed probing nodes so as to measure a large-scale Ethereum network at a low cost. We run DEthna on Goerli (the most popular Ethereum test network) to evaluate its capability in discovering network topology. The experimental results demonstrate that DEthna significantly outperforms the state-of-the-art baselines. Based on DEthna, we further analyze characteristics of the Ethereum network revealing that there exist more than 50% low-degree Ethereum nodes that weaken the network robustness.
Eric Venner, Mullai Murugan, Walker Hale, Jordan M Jones · 7 authors
MOTIVATION: Clinical genome sequencing laboratories return reports containing clinical testing results, signed by a board-certified clinical geneticist, to the ordering physician. This report is often a PDF, but can also be a paper copy or a structured data file. The reports are frequently modified and reissued due to changes in variant interpretation or clinical attributes. MATERIALS AND METHODS: To precisely track report authenticity, we developed ARBoR (Authenticated Resources in a Hashed Block Registry), an application for tracking the authenticity and lineage of versioned clinical reports even when they are distributed as PDF or paper copies. ARBoR tracks clinical reports as cryptographically signed hash blocks in an electronic ledger file, which is then exactly replicated to many clients. RESULTS: ARBoR was implemented for clinical reporting in the Human Genome Sequencing Center Clinical Laboratory, initially as part of the National Institute of Health's Electronic Medical Record and Genomics (eMERGE) project. CONCLUSIONS: To date, we have issued 15 205 versioned clinical reports tracked by ARBoR. This system has provided us with a simple and tamper-proof mechanism for tracking clinical reports with a complicated update history.
Representing the semantic relations that exist between two given words (or entities) is an important first step in a wide-range of NLP applications such as analogical reasoning, knowledge base completion and relational information retrieval. A simple, yet surprisingly accurate method for representing a relation between two words is to compute the vector offset (\PairDiff) between the corresponding word embeddings. Despite its empirical success, it remains unclear whether \PairDiff is the best operator for obtaining a relational representation from word embeddings. In this paper, we conduct a theoretical analysis of the \PairDiff operator. In particular, we show that for word embeddings where cross-dimensional correlations are zero, \PairDiff is the only bilinear operator that can minimise the $\ell_{2}$ loss between analogous word-pairs. We experimentally show that for word embedding created using a broad range of methods, the cross-dimensional correlations in word embeddings are approximately zero, demonstrating the general applicability of our theoretical result. Moreover, we empirically verify the implications of the proven theoretical result in a series of experiments where we repeatedly discover \PairDiff as the best bilinear operator for representing semantic relations between words in several benchmark datasets.