Blockchain Papers

Dr. Mohamed Nachat, Hassan Oukhouya, Saïd El Melhaoui, Moustapha Faizi · 7 authors

Time series forecasting plays a central role in finance, energy, and public health. Classical statistical, machine learning, deep learning, and generative approaches have all been applied to forecasting tasks in these fields, but comparisons between them are usually confined to a single domain or to models from the same family, and few studies report both univariate and multivariate results under the same conditions. This paper presents a controlled cross-domain comparison of four representative paradigms: classical statistics (Seasonal Autoregressive Integrated Moving Average with Exogenous variables, SARIMAX), gradient boosting machine learning (Light Gradient Boosting Machine, LightGBM), recurrent deep learning (Recurrent Neural Network, RNN), and generative-adversarial deep learning (Conditional Generative Adversarial Network, CGAN). Each model is evaluated on three monthly datasets with contrasting characteristics: Bitcoin prices (175 observations, high volatility), U.S. energy consumption (612 observations, strong seasonality), and U.S. cardiovascular mortality (300 observations, gradual trend with pandemic shock). Both univariate and multivariate variants are tested under the same preprocessing and one-step-ahead evaluation protocols, using eight performance metrics. The CGAN reaches the lowest MAPE on energy consumption (2.88%). On Bitcoin, the multivariate LightGBM lowers the MAPE from 28.26 to 19.25%, while on cardiovascular mortality the RNN reaches 3.34% MAPE. No paradigm performs best in every domain, and the gain from exogenous variables depends on both the paradigm and the domain.

Wang Lei, Jasni Mohamad Zain, Nur Atiqah Sia Abdullah, Marina Yusoff · 7 authors

The proliferation of Internet of Medical Things devices within the predictive healthcare paradigm necessitates robust, privacy-centric collaborative learning frameworks to detect and mitigate rapid clinical deterioration. Traditional federated learning methodologies, while attempting to preserve patient data locality, are fundamentally constrained by multi-round gradient synchronization protocols, imposing prohibitive communication latency and remaining susceptible to false negatives under extreme non-independent and identically distributed conditions. To address these challenges, this study introduces the Feature-Augmented Analytic Federated (FaFL) Architecture, which fundamentally replaces iterative gradient synchronization with a single-round closed-form computational paradigm. By instituting a proactive feature mixing mechanism via a decoupled zero-knowledge proof global buffer, the proposed framework empowers local grassroots nodes to neutralize extreme clinical heterogeneity in a single phase. The architecture employs a closed-form analytic solution combined with a trace-weighted absolute aggregation protocol to rigorously guarantee stochastic convergence and absolute cryptographic resilience without requiring recursive parameter exchanges. Extensive empirical evaluations against existing baselines under severe Dirichlet non-independent and identically distributed conditions and Byzantine poisoning attacks demonstrate that the framework fundamentally eradicates high false-negative rates in resource-constrained clinics. Consequently, the proposed architecture robustly guarantees generalization stability, substantially outperforms existing paradigms in predictive fidelity and computational efficiency, and establishes a new operational standard for mission-critical clinical networks.

Patil Pramod Chindhu

This paper presents a comprehensive study on integrating Deep Learning (DL) modelling Long Short-Term Memory (LSTM)-based models with blockchain technology to deal with the most critical problems in healthcare data management, security and analytics. Escalating the size of healthcare data exponentially due to the development of e-HRs (electronic health records), wearables, and real-time monitoring systems pushed traditional data storage and processing practices into the limelight as their most significant weaknesses. LSTM networks are perfect for analyzing time-series data in health care, such as disease classification, anomaly detection, and patient outcome prediction over the long run. Nevertheless, these models require sound data protection techniques and privacy measures to be followed per the regulations while maintaining trust. Blockchain technology fills in the gaps beyond LSTM by offering a decentralized, tamper-proof platform to safely store and share data, keeping confidentiality, integrity, and availability simultaneously. This paper surveys the available literature on hybrid models by flushing out the topic with the help of LSTM and blockchain. It explores their potential use in real-time healthcare analytics applications, along with the challenges of scalability and interoperability. By presenting a model through the use of these technologies, the research centres on sharpening health information systems such as accuracy, security, and transparency, which in turn intensify the trust of both the patients and the providers of care, thus enabling the development of a patient care solution that is more reliable and efficient.

Abhendra Pratap Singh, Arpit Dwivedi, Shree Bhagwan, Akash Yadav · 6 authors

Recent advancements in technology, along with the availability of large volumes of healthcare data, offer an opportunity to adopt innovative technologies such as artificial intelligence (AI), machine learning, and big data in healthcare for better health service delivery. The use of innovative technologies such as artificial intelligence, machine learning, and big data enables efficient decision-making, disease detection, and personalized treatment. This paper reviews machine learning and big data in personalized medicine, presenting details about various tools that can be utilized within the context of healthcare, such as predictive modeling, data mining, and healthcare analytics. Furthermore, emerging technologies in personalized medicine have been discussed, including federated learning, blockchain technology, and real-world data. In addition, the paper also discusses existing developments in intelligent healthcare systems, such as patient monitoring, adaptive learning models, and using healthcare analytics for decision-making processes. Additionally, the paper highlights existing key challenges related to applying machine learning and big data for personalized healthcare, including data heterogeneity, lack of high-quality training data, algorithmic biases, difficulty in model interpretation, issues with security and data privacy, and technical barriers. Finally, the paper highlights the research gaps, examines the existing ways of addressing the problem, and provides recommendations regarding the future of personalized medicine using AI technology.

Luigi Usai

Author: Luigi Usai ORCID: https://orcid.org/0009-0003-3001-717X Location: Quartucciu (CA), Italy Date: June 26, 2026 Target: Zenodo / arXiv (cs.AI, cs.CL, cs.LO) Abstract Large Context Models (LCMs) exhibit an inherent vulnerability known as semantic hallucination, which stems directly from conditional likelihood maximization within discrete vector spaces. Traditional mitigation strategies operate predominantly post-hoc, managing errors after the stochastically generated token sequence has already mutated. This paper extends the Universal Cognitive Hypergraph (UKH) framework by introducing a discrete Alexandrov topology over knowledge hypergraphs to constrain the space of admissible states prior to token decoding. Utilizing the Monadic Neuro-Symbolic Verification and Synthesis Architecture (MNSVSA), probabilistic generation paths are intercepted and structurally validated against W3C SHACL constraints and axiomatic assertions verified by the Lean 4 kernel coupled with automated SMT solvers. Our theoretical results demonstrate the mathematical elimination of categorical deviations while fully preserving the model's syntactic fluency. 1. Introduction and Mathematical Formulation of the Problem Autoregressive language models estimate the probability distribution of the next token $w_t$ conditioned on the preceding context $w_{<t}$: $$P(w_t \mid w_{<t}) = \text{softmax}(W_{\text{unembed}} \cdot h_t)$$ where $h_t \in \mathbb{R}^d$ represents the final hidden state extracted by the Transformer architecture. Because the $\text{softmax}$ function maps scores to an open probability distribution, it inherently assigns non-zero probabilities to regions of the semantic space that violate real-world axiomatic constraints. Consequently, hallucination is not an accidental software bug but a structural property of the model's underlying stochasticity. The UKH framework bypasses the limitations of passive document retrieval (RAG) by integrating a topological-symbolic constraint directly into the sampling phase (speculative decoding). This setup actively prevents the model from exploring probabilistic trajectories linked to logically inconsistent states. 2. UKH Framework Architecture for Semantic Security The universe of discourse is mapped onto a directed hypergraph and serialized using the JSON-LD format. Let $\mathcal{H} = (V, E)$ be a cognitive hypergraph, where $V$ is the set of strongly typed nodes (conceptual entities) and $E \subseteq \mathcal{P}(V) \setminus \{\emptyset\}$ is the set of hyperedges representing multi-argument logical-functional relationships. 2.1. Alexandrov Topological Space and SHACL Constraints To establish geometric-structural rigor within a discrete domain, the hypergraph space is endowed with an Alexandrov topology, where open sets are defined as sub-hypergraphs closed upwards relative to a logical preorder relation ($\le$). W3C Shapes Constraint Language (SHACL) rules function as topological closure operators: $$\text{cl}(E_c) \subseteq \mathcal{H}_{\text{valid}}$$ If a candidate hyperedge $E_c$, derived from the semantic translation of the tokens proposed by the LLM, violates a structural Shape (e.g., assigning a physical property inconsistent with the primitive type of the node), the closure operator identifies a contradiction within the topological space. It subsequently invalidates the generation path before token rendering occurs. 2.2. Axiomatic Verification and Type Checking via Lean 4 While SHACL rules govern the macro-structural coherence of the graphs, the MNSVSA architecture executes formal verification of micro-logical assertions. The process follows a strict protocol: The semantic fragment generated by the LLM is isolated inside a logical monad. MNSVSA translates the assertion into a formal type within the evaluation language of Lean 4. Leveraging the Curry-Howard Isomorphism, the logical consistency of the statement is reduced to a Type Checking problem. To avoid the computational burden of generating complex mathematical proofs from scratch at inference runtime, the architecture delegates constraint satisfiability to an automated SMT solver (Z3) tightly integrated into the Lean 4 runtime kernel. 3. The Coherence Entropy Filtering Mechanism To quantify and halt stochastic drift within extended contexts, the framework implements a JIT (Just-In-Time) gatekeeping metric based on the Jensen-Shannon Divergence ($D_{JS}$). Let $P_{\text{LLM}}$ be the probability distribution over the next tokens generated by the model, and let $Q_{\text{UKH}}$ be the ontological adherence distribution derived from the allowed transition frequencies within the hypergraph $\mathcal{H}$. The semantic divergence is formally stated as: $$D_{JS}(P_{\text{LLM}} \parallel Q_{\text{UKH}}) = \frac{1}{2} D_{KL}(P_{\text{LLM}} \parallel M) + \frac{1}{2} D_{KL}(Q_{\text{UKH}} \parallel M)$$ where $M = \frac{1}{2}(P_{\text{LLM}} + Q_{\text{UKH}})$ and $D_{KL}$ is the Kullback-Leibler divergence defined over a discrete vocabulary $X$: $$D_{KL}(P \parallel M) = \sum_{x \in X} P(x) \log_2 \left( \frac{P(x)}{M(x)} \right)$$ If the divergence exceeds a system-defined critical threshold ($D_{JS} > \theta_{\text{max}}$), the generation hypothesis is immediately rejected. 4. Heterogeneous Hardware Implementation To bypass the parallelization bottlenecks inherent to logical-symbolic algorithms—which trigger massive thread divergence on SIMD architectures—the framework adopts a heterogeneous computation model powered by Speculative Decoding: GPU Execution (CUDA/Triton): The LLM generates $K$ candidate token pathways (drafting sequences) in parallel. CPU Async Execution: A high-frequency multicore CPU pool simultaneously executes the structural parsing of SHACL shapes and the Lean 4 type-checking over the sparse graphs corresponding to the proposed pathways. Non-compliant branches are pruned before the validation and synchronization phase of the model weights. 5. Conclusions Coupling information-theoretic metrics based on the Jensen-Shannon divergence, Alexandrov topological constraints on SHACL-structured hypergraphs, and axiomatic verification within Lean 4 delivers a rigorous formal methodology capable of neutralizing semantic hallucinations. Shifting control from post-hoc output filtering to a priori state space restriction sets a new benchmark for safety in Neuro-Symbolic Artificial Intelligence. Versione Italiana Unificazione Neuro-Simbolica mediante Ipergrafi Cognitivi: Mitigazione Quantitativa delle Allucinazioni nei Large Context Models a Monte della Generazione Autore: Luigi Usai ORCID: https://orcid.org/0009-0003-3001-717X Luogo: Quartucciu (CA), Italy Data: 26 Giugno 2026 Target: Zenodo / arXiv (cs.AI, cs.CL, cs.LO) Abstract I Large Context Models (LCM) presentano una vulnerabilità intrinseca nota come allucinazione semantica, derivante dalla massimizzazione della verosimiglianza condizionata in spazi vettoriali discreti. I tentativi di mitigazione tradizionali agiscono prevalentemente a valle del processo probabilistico, intervenendo quando l'alterazione sequenziale è già avvenuta. Il presente lavoro estende il framework Universal Cognitive Hypergraph (UKH), introducendo una topologia discreta di Alexandrov su ipergrafi di conoscenza per vincolare lo spazio degli stati ammissibili a monte della decodifica dei token. Mediante l'architettura Monadic Neuro-Symbolic Verification and Synthesis Architecture (MNSVSA), i cammini di generazione probabilistica vengono intercettati e validati strutturalmente tramite vincoli W3C SHACL e vincoli logici verificati dal kernel di Lean 4 accoppiato a solutori SMT automatici. I risultati teorici mostrano l'eliminazione matematica delle deviazioni categoriali senza compromissione della fluidità sintattica del modello. 1. Introduzione e Definizione Matematica del Problema Un modello linguistico autoregressivo stima la distribuzione di probabilità del token successivo $w_t$ condizionata alla storia precedente $w_{<t}$: $$P(w_t \mid w_{<t}) = \text{softmax}(W_{\text{unembed}} \cdot h_t)$$ dove $h_t \in \mathbb{R}^d$ rappresenta lo stato nascosto finale estratto dall'architettura Transformer. Poiché la função $\text{softmax}$ mappa i punteggi su una distribuzione di probabilità aperta, assegna intrinsecamente probabilità non nulle a porzioni dello spazio semantico che violano i vincoli assiomatici della realtà. Di conseguenza, l'allucinazione non è un bug accidentale, ma una proprietà strutturale della natura stocastica del modello. Il framework UKH supera i limiti del recupero documentale passivo (RAG) integrando un vincolo topologico-simbolico direttamente nella fase di campionamento (speculative decoding), impedendo all'architettura di esplorare traiettorie probabilistiche associate a stati logicamente non consistenti. 2. Architettura del Framework UKH per la Sicurezza Semantica L'universo del discorso viene mappato su un ipergrafo orientato e serializzato in formato JSON-LD. Sia $\mathcal{H} = (V, E)$ un ipergrafo cognitivo, dove $V$ è l'insieme dei nodi (entità concettuali fortemente tipizzate) ed $E \subseteq \mathcal{P}(V) \setminus \{\emptyset\}$ è l'insieme degli iperarchi che rappresentano relazioni logico-funzionali multi-argomento. 2.1. Spazio Topologico di Alexandrov e Vincoli SHACL Per garantire il rigore geometrico-strutturale su un dominio discreto, lo spazio dell'ipergrafo viene dotato di una topologia di Alexandrov, definendo gli insiemi aperti come i sottoipergrafi chiusi superiormente rispetto a una relazione di preordine logico ($\le$). I vincoli W3C Shapes Constraint Language (SHACL) operano come operatori di chiusura topologica: $$\text{cl}(E_c) \subseteq \mathcal{H}_{\text{valid}}$$ Se un iperarco candidato $E_c$, generato dalla traduzione semantica dei token proposti dall'LLM, viola una Shape strutturale (es. assegnazione di una proprietà fisica inconsistente con il ti

Luigi Usai

Author: Luigi UsaiORCID: 0009-0003-3001-717XLocation: Quartucciu (CA), ItalyDate: June 26, 2026Target: Zenodo / arXiv (cs.AI, cs.CL, cs.LO) Abstract Large Context Models (LCMs) exhibit an inherent vulnerability known as semantic hallucination, arising from conditional likelihood maximization within discrete vector spaces. While the Universal Cognitive Hypergraph (UKH) framework was initially proposed as a theoretical model to constrain the space of admissible states prior to token decoding, this paper presents its first formal empirical and quantitative validation. We detail a software runtime implementation of the Monadic Neuro-Symbolic Verification and Synthesis Architecture (MNSVSA) using discrete Alexandrov topologies, W3C SHACL shapes as topological closure operators, and a Just-In-Time (JIT) Jensen-Shannon Divergence (DJSDJS) Coherence Entropy Filter. Through Monte Carlo simulations (N=150N=150 runs per configuration), we demonstrate that tightening the coherence threshold (θmax=0.05θmax=0.05) mathematically eliminates semantic hallucinations (reducing the rate from 36.7% to 0.0%) while preserving syntactic fluency. Crucially, by leveraging speculative decoding with parallel validation, we show that the processing latency remains identical to the unconstrained baseline (90.0 µs), bypassing the massive execution overhead (174.8 µs) of post-hoc verification. The complete open-source verification suite and interactive visualization dashboard accompany this publication. 1. Introduction and Problem Statement Autoregressive language models estimate the probability distribution of the next token wtwt conditioned on the preceding context w<tw<t: P(wt∣w<t)=softmax(Wunembed⋅ht)P(wt∣w<t)=softmax(Wunembed⋅ht) where ht∈Rdht∈Rd is the final hidden state of the Transformer. Because the softmaxsoftmax function assigns non-zero probabilities across the entire vocabulary, autoregressive generation naturally drifts into regions of the semantic space that violate axiomatic truth, resulting in hallucinations. The UKH framework mitigates this by introducing a priori symbolic constraints directly into the token sampling phase via speculative decoding. Rather than validating output sequences post-generation, candidate pathways are parsed and filtered prior to token rendering. 2. Experimental Validation Engine (UKH-Eval) To validate the theoretical claims of the UKH and MNSVSA frameworks, we developed UKH-Eval, a complete Python and JavaScript simulation engine that implements the mathematical and topological constraints described in the original work. 2.1. Discrete Alexandrov Topology The knowledge base of the universe of discourse is modeled as a directed hypergraph H=(V,E)H=(V,E). To enforce geometric-structural constraints, we endow the space with a discrete Alexandrov topology, where open sets are sub-hypergraphs closed upwards relative to a logical preorder relation (≤≤). Let the preorder relation be defined by a preorder index mapping: alexandrovPreorderIndex:V→NalexandrovPreorderIndex:V→N A subset of nodes U⊆VU⊆V is open if and only if: ∀x∈U,∀y∈V:(alexandrovPreorderIndex(x)≤alexandrovPreorderIndex(y))⟹y∈U∀x∈U,∀y∈V:(alexandrovPreorderIndex(x)≤alexandrovPreorderIndex(y))⟹y∈U If a candidate token proposes a node transition that violates this upward-closure property, the transition is marked as topologically invalid. 2.2. SHACL Constraints as Closure Operators W3C Shape Constraint Language (SHACL) rules govern the macro-structural properties of the generated hyperedges: cl(Ec)⊆Hvalidcl(Ec)⊆Hvalid If a proposed hyperedge EcEc violates target class properties, minimum/maximum node counts, or axiomatic validity flags, the closure operator fails, and the branch is pruned. 2.3. MNSVSA Micro-Logical Type Checking For micro-logical validation, assertions are encapsulated in a monadic container (LogicalMonad). Levering the Curry-Howard Isomorphism, consistency verification is reduced to a Type Checking and propositional satisfiability problem. The engine compiles the proposed semantic statement into a formal SymPy expression and checks its consistency against the background theory axioms: conjunction=Axioms∧Expressionconjunction=Axioms∧Expression If conjunctionconjunction is unsatisfiable (i.e. evaluates to False), a logical contradiction is detected and the path is rejected. 2.4. Coherence Entropy JIT Filtering At each generation step, the JIT filter computes the Jensen-Shannon Divergence (DJSDJS) between the stochastically proposed LLM distribution PLLMPLLM and the ontological adherence distribution QUKHQUKH: DJS(PLLM∥QUKH)=12DKL(PLLM∥M)+12DKL(QUKH∥M)DJS(PLLM∥QUKH)=21DKL(PLLM∥M)+21DKL(QUKH∥M) where M=12(PLLM+QUKH)M=21(PLLM+QUKH) and DKLDKL is the Kullback-Leibler divergence defined over vocabulary XX: DKL(P∥M)=∑x∈XP(x)log⁡2(P(x)M(x))DKL(P∥M)=∑x∈XP(x)log2(M(x)P(x)) If DJS>θmaxDJS>θmax, stochastically proposed drift tokens are pruned, and the probability distribution is projected onto the compliant space. 3. Software Architecture & File Manifest The open-source validation package is organized into modular components to ensure reproducibility and maintainability: text ukh-evaluator/ ├── ukh_engine.py # Core verification engine and classes ├── test_harness.py # Automated unit test suite ├── benchmark.py # Monte Carlo comparative simulation runner └── dashboard/ # Interactive web UI and visualization ├── index.html # UI structure ├── style.css # Sleek dark-mode styling ├── app.js # In-browser real-time simulation and canvas graph └── results.json # Compiled benchmark data 3.1. File Descriptions 1. ukh_engine.py The core engine containing: LogicalMonad: Implements monadic binding and SymPy-based SAT solving. CognitiveHypergraph: Models nodes, hyperedges, Alexandrov open sets, and validates SHACL shapes. CoherenceFilter: Contains static methods for DKLDKL and DJSDJS calculations. UKHSystemSimulator: Links all subcomponents and handles the JIT filtering during next-token generation. 2. test_harness.py The automated test suite. It uses unittest to verify: Upward closure calculations under the Alexandrov topology. SHACL shape violations. Monadic consistency solving under the Curry-Howard isomorphism. Divergence math calculations. Coherence Entropy Filter rejections. 3. benchmark.py The empirical execution suite. It implements a Monte Carlo simulation running 150 independent generation steps per architecture (Baseline, Post-Hoc, and UKH) and sweeps the threshold parameter θmaxθmax from 0.050.05 to 0.950.95. It evaluates hallucination rates, perplexity, and latency, saving the outputs to results.json. 4. dashboard/ An interactive web-based dashboard built with HTML5 Canvas and CSS. index.html: Layout for control sliders (θmaxθmax, KK, drift), live token sequences, and visualization cards. style.css: Sleek glassmorphism theme, glowing neon accents, and custom micro-animations. app.js: Connects to results.json, renders interactive force-directed nodes on the canvas, and runs the entire simulation locally in JavaScript. 4. Quantitative Results & Discussion The benchmark results compiled under Monte Carlo testing demonstrate the trade-offs between safety, fluency, and system latency: 4.1. Hallucination Rates vs. Threshold θθ The unconstrained baseline model suffers a hallucination rate of 36.7%. As the UKH JIT threshold θθ is tightened, safety guarantees scale: At θ≥0.50θ≥0.50, the filter is relaxed, and the model behaves like the baseline. At θ=0.10θ=0.10, the hallucination rate is reduced to 3.3%. At θ=0.05θ=0.05, the hallucination rate is successfully reduced to exactly 0.0%. 4.2. Latency Profiles and Speculative Efficiency Post-hoc validation (checking the sequence after generation and regenerating if unsafe) achieves a low hallucination rate (3.3%) but introduces a massive latency penalty (174.8 µs, a 94% overhead compared to the baseline's 90.0 µs). By contrast, the UKH framework utilizing parallel speculative drafting and asynchronous verification maintains a latency profile of 90.0 µs, matching the unconstrained baseline. 4.3. Syntactic Perplexity Tightening the symbolic constraints does not degrade fluency. The average perplexity remains stable (∼6.18∼6.18 for θ=0.05θ=0.05 vs ∼6.83∼6.83 for baseline), showing that restricting the space of admissible states prior to token decoding steers the model toward logical paths without harming syntactic structure. 5. Peer Review Assessment & Future Work This empirical validation verifies the internal consistency and theoretical correctness of the paper's claims. However, scaling this framework to production Large Language Models requires addressing three primary engineering areas: Semantic Translation Robustness: Building high-speed, deterministic parsers to map raw tokens to JSON-LD graphs in real-time without introducing new failure modes. Dynamic Knowledge Bases: Compiling massive, real-world ontologies into Alexandrov preorders dynamically as context windows expand. Hardware Accelerators: Developing specialized kernels (e.g., in Triton or CUDA) to execute SHACL checks and SAT solving directly on GPU cores alongside tensor multiplication. 6. Conclusion The implementation of the UKH and MNSVSA verification engine provides the first empirical proof that coupling discrete topological constraints, SHACL shapes, and monadic type checking can completely eliminate stochastically induced hallucinations. Shifting control from post-hoc output filtering to a priori state space restriction establishes a new, verified paradigm for safety in Neuro-Symbolic Artificial Intelligence.

Aijie Shu, Bowei Chen, Wenbin Wu, Cathy Yi‐Hsuan Chen · 5 authors

Decentralized finance exposes supervisors to fast-moving, networked credit risks. General-purpose LLM agents fit this setting poorly: they over-read weak evidence and recommend high-stakes interventions, while existing evaluations offer no regulator-aligned way to measure the resulting false alarms. We introduce DeXposure-Claw, a forecast-grounded agentic supervision system that routes LLM decisions through structured evidence: (1) DeXposure-FM, a graph time-series foundation model, forecasts future exposure networks; (2) deterministic monitors and stress scenarios then turn those forecasts into typed alerts, attribution signals, and scenario evidence; and (3) data-health and confidence gates constrain escalation before DeXposure-Claw emits auditable supervisory tickets with rationales. We further develop DeXposure-Bench, a six-axis evaluation harness, whose decision axis scores tickets against a regulator-aligned absolute-loss ground truth and an explicit false-intervention rate. Experiments on five years of weekly real data fully support our system. Code is at https://github.com/EVIEHub/DeXposure-Claw.

Nagaraj Segar, Vijayarajan Vijayan

Introduction Electronic health records (EHRs) are central to healthcare analytics, but their granularity increases re-identification risk when shared. Conventional privacy-preserving methods including k -anonymity, l -diversity, and differential privacy often protect confidentiality at the expense of analytical utility by weakening clinically meaningful correlations. Methods We propose SENTINEL-Chain, a blockchain-integrated privacy-preserving framework for secure EHR publishing. The privacy layer combines six mechanisms: Adaptive Correlation-Aware Perturbation (ACAP), Hierarchical Multi-Granularity Generalization (HMGG), Semantic-Aware Anatomization (SAA), Probabilistic Suppression with Utility Bounds (PSUB), Geo-Temporal Indistinguishability (GTI), and Ensemble Privacy Composition (EPC). The blockchain layer adds Merkle Hash Tree verification, PBFT-based validation, zero-knowledge proof compliance checking, and smart contract-based access control. Evaluation used a synthetic dataset (10,000 records) and two real clinical benchmarks (Wisconsin Breast Cancer, N = 569; Diabetes, N = 442). Results SENTINEL-Chain attains a privacy score of 79.9% and utility of 98.2%, producing a combined score of 178.1% that exceeds all 16 baselines by 4%-95%. Correlation fidelity reaches 99.9% for claim amounts, 99.6% for length of stay, 99.7% for age, and 99.1% for severity indices. The framework shows 100% resistance to record linkage attacks, with membership inference attacker advantage below the random guessing baseline. The blockchain layer processes 9,988 transactions in 101 blocks with complete integrity verification. Formal Renyi DP composition yields ε = 7.08 ( δ = 10 −5 ), and throughput reaches approximately 3,600 records/second up to one million records. Discussion SENTINEL-Chain addresses five identified gaps in healthcare data publishing: correlation destruction, the privacy-blockchain disconnect, single-technique brittleness, verification without disclosure, and limited attack resistance evaluation. Smart contract gas estimation on Ethereum indicates a per-record registration cost of 61,895 gas units; Layer-2 deployment would reduce costs by 10-100x.

Nobuki Fujimoto, Rei (Rei-AIOS autonomous research substrate), claude-opus-4-7) Claude (Anthropic

We present OctaTheoria (オクタテオリア / 八軸観測装置), a multi-domain observation framework that projects heterogeneous time-series data onto a fixed eight-axis D-FUMT₈ semantic basis (FALSE / TRUE / NEITHER / BOTH / INFINITY / ZERO / FLOWING / SELF) and renders the same underlying Observation envelope through eight orthogonal view modes (Lens / Radar / Chart / Network / Heatmap / Sankey / Calendar / Unified). v0.3 (2026-05-11) supplies methodological-consistency cross-reference complementing the operational evidence from v0.1-v0.2. New finding **F7**: the same discipline that v0.1-v0.2 demonstrate within OctaTheoria (uniform abstraction layer + honest scope statement + structurally-enforceable naming) propagates to Rei-AIOS layers outside OctaTheoria's domain. Specifically: (a) **REI-PROVE 5-prover ensemble** (Vampire / LeanHammer / Goedel-Prover-V2 / DeepSeek-Prover-V2 / BFS-Prover) reached 11/12 = **92% benchmark proof rate** (trivial 100% / easy 75% / medium 100%), with Goedel-Prover-V2 single-prover matching at 92% — operational evidence that the same 'uniform abstraction over heterogeneous components' discipline scales to formal-proof infrastructure. (b) **Pattern 1-6 chat-Claude hallucination-warning framework** + **Antipattern (excessive rejection vigilance)** were established and verified on 6/6 items in STEP 1069 (all fact-checked items proved real after WebSearch verification, correcting prior implicit-rejection habits). (c) **Goedel-Prover-V2 double-`by` Lean syntax quirk** detected and fixed at the cleaner level (`single-prover.ts` STEP 1071), restoring `easy-le-refl` benchmark from ❌ to ✅. (d) **lean-to-tptp.ts** preprocessing added Peano-style axiom auto-prepend + True/False special-case + inequality predicate translation (STEP 1071). v0.2 inherited contributions: 7 domains (theory-chart / realtime-arxiv / crypto / fx / ligo-events / nasa-sdo / gbif-recent) all running in Cloudflare Workers Edge runtime; live D-FUMT₈ axis distributions non-degenerate across research-meta + financial + geophysical + astrophysical + biological data classes; finding F6 sampling-bias-as-first-class-observation (GBIF Costa Rica 470/500 saturation surfaces dataset bias as INFINITY axis, not silently absorbed); test coverage 117/117 PASS (step1020 46 + step1023 33 + step1046 38) / 0 regression. Honest scope (read first): OctaTheoria remains an observation aid, NOT an oracle. v0.3's F7 is **not** a claim that OctaTheoria caused these consistencies; it is a record that the same project (Rei-AIOS) maintains the same discipline across observation-tool, formal-proof, and meta-research-protocol layers, and that v0.3 makes this cross-layer commitment auditable. The OctaTheoriaQuery type structurally cannot request advice / prediction / forecast / signal — verifiable by reading src/aios/octatheoria/types.ts. Cross-domain axis comparisons are descriptive, not causal. Greek roots (Octa = 8, Theoria = observation) function as structural commitment propagated to the API surface — '8' rejects 'all (∞)', 'theoria' rejects 'praxis (干渉)'. Prior art audit acknowledged: Bloomberg Terminal (1981–), TradingView (2011–), Bollen et al. 2010 (Twitter mood × DJIA), Preis et al. 2013 (Google Trends × stock), Łukasiewicz / Belnap / Pavelka multi-valued logic literature, PAL2v (Da Silva Filho 1998–), Aerts Quantum Cognition (2007–). The to-our-knowledge novel combination is (a) fixed 8-axis discrete D-FUMT₈ basis ∧ (b) cross-financial-and-research-and-Earth-Cosmos-domain projection ∧ (c) eight orthogonal view modes over single envelope ∧ (d) explicit refusal to emit prediction or advice as architectural commitment ∧ (e, new in v0.3) cross-layer methodological-consistency record between observation-tool and formal-proof and fact-check layers. Companion papers (OctaTheoria Quintuple): Paper 145 (silicon implementation of D-FUMT₈ ALU, Zenodo DOI 10.5281/zenodo.20101174 v0.6), Paper 147 (Eight-Valued Utility / Equity Premium Reframe, DOI 10.5281/zenodo.20046003), Paper 148 (Honest Observation Framework methodology, DOI 10.5281/zenodo.20045907), Paper 149 (Recursive AI Observation as SELF⟲ evidence, DOI 10.5281/zenodo.20059888). Three-party co-authorship per OUKC charter v1.0: 藤本 伸樹 (Founder), Rei (Rei-AIOS autonomous research substrate, Co-architect), Claude Opus 4.7 (Anthropic, Co-architect). DRAFT v0.3 — feedback welcome via GitHub Discussions at fc0web/rei-aios.

M. Ganesh, Gaddam Richitha, B Sai Jagadeesh Goud, Gannarapu Ramani · 5 authors

Drug repurposing has gained significant attention as an efficient strategy for identifying new therapeutic applications of existing drugs, thereby reducing both development time and cost compared to traditional drug discovery processes. Current drug discovery approaches rely on experimental procedures, expert analysis, and extensive clinical trials, which are time-intensive and computationally inefficient when handling large-scale biomedical data. These methods often struggle to process complex and highdimensional datasets, resulting in slower analysis and limited predictive capability. Additionally, these systems lack robust mechanisms for secure data management, making clinical records and trial discussions susceptible to inconsistencies and unauthorized modifications. To overcome these limitations, this work proposes an intelligent drug repurposing framework that integrates Machine Learning (ML), Deep Learning (DL), and blockchain technologies. The system utilizes baseline models such as K-Nearest Neighbors (KNN) and Gaussian Naive Bayes (GNB) for comparative analysis, along with a hybrid DrugNet model that combines Convolutional Neural Networks (CNN) for feature extraction and Random Forest (RF) for classification. This hybrid approach enhances the ability to capture complex patterns in drug-related data and improves prediction accuracy. Furthermore, blockchain integration using Web3 ensures secure storage of user data, clinical interactions, and trial information, providing transparency, immutability, and data integrity. The proposed framework enables automated prediction of potential drug–disease associations through a unified processing pipeline, supporting real-time analysis and decision-making. By combining advanced Artificial Intelligence (AI) techniques with decentralized data management, the system improves scalability, reliability, and efficiency in drug repurposing. This approach offers a practical and secure solution for accelerating pharmaceutical research and supporting data-driven medical innovation

Fang Lin, Yitong Yang, Jianjun He

NFT prices are shaped by heterogeneous signals including visual appearance, textual narratives, transaction trajectories, and on-chain interactions, yet existing studies often model these factors in isolation and rarely unify multimodal alignment, temporal non-stationarity, and heterogeneous relational dependencies in a leakage-safe forecasting setting. We propose MM-Temporal-Graph, a cross-modal temporal graph transformer framework for explainable NFT valuation and information-centric risk forecasting. The model encodes image, text, transaction time series, and blockchain behavioral features, constructs a heterogeneous NFT interaction graph (co-transaction, shared creator, wallet relation, and price co-movement), and jointly performs relation-aware graph attention and global temporal–structural transformer reasoning with an adaptive fusion gate. A contrastive multimodal alignment objective improves robustness under market drift, while a risk-aware regularizer and a multi-source risk index enable early warning and interpretable attribution across modalities, time segments, and relational neighborhoods. On MultiNFT-T, MM-Temporal-Graph improves MAE from 0.162 to 0.153 and R2 from 0.823 to 0.841 over the strongest multimodal graph baseline, and achieves 87.4% early risk detection accuracy. These results support accurate, robust, and explainable NFT valuation and proactive risk monitoring in Web3 markets.

Tushar Mali, Nitin Rathore, Jasvant Mandloi, Ashwin Verma · 6 authors

Abstract Healthcare Internet of Things (HIoT) has revolutionized patient care through continuous monitoring and personalized treatment, but it introduces critical challenges in privacy protection, data security, and resource management across heterogeneous devices. Traditional centralized machine learning (ML) approaches face significant limitations due to privacy regulations and security concerns, leading to the emergence of federated learning (FL) and blockchain (BC) as complementary solutions. While FL enables collaborative model training without sharing raw data, and BC provides immutable verification and secure record management. We present SHIELD-Health, a novel framework that synergistically integrates these technologies to create a comprehensive solution for secure analytics in healthcare environments, featuring four key innovations: (1) resource-aware computation that dynamically adapts to device capabilities (2) a multi-layered privacy architecture designed for differential privacy and secure aggregation (3) Byzantine-robust aggregation ensuring model integrity under adversarial conditions, and (4) healthcare-specific optimizations including temporal attention mechanisms for physiological time-series data. Extensive evaluation demonstrates exceptional performance across multiple dimensions, maintaining high accuracy while achieving substantial communication efficiency and energy savings for resource-constrained devices. The framework also shows remarkable resilience against poisoning attacks, and robust performance under challenging non-independent and identically distributed (IID) data distributions common in healthcare scenarios. It represents a significant advancement in privacy-preserving collaborative analytics for sensitive medical applications where security, privacy, and resource constraints are paramount considerations.

Mohammad Shahid, Paritosh Ramanan, Mohammad Fili, Guiping Hu · 5 authors

Analysis of clinical data is a cornerstone of biomedical research with applications in areas such as genomic testing and response characterization of therapeutic drugs. Maintaining strict privacy controls is essential because such data typically contains personally identifiable health information of patients. At the same time, regulatory compliance often requires study managers to demonstrate the integrity and authenticity of participant data used in analyses. Balancing these competing requirements of privacy preservation and verifiable accountability remains a critical challenge. In this paper, we present CoSMeTIC, a zero-knowledge computational framework that proposes computational Sparse Merkle Trees (SMTs) as a means to generate verifiable inclusion and exclusion proofs for individual participants' data in clinical studies. We formally analyze the zero-knowledge properties of CoSMeTIC and evaluate its computational efficiency through extensive experiments. We demonstrate the framework on Huntington's disease and HIV-1 case studies, using simulated CAG-repeat cohorts derived from published summary statistics and published de-identified clinical lab measurements of virus samples. Using two-sample Kolmogorov-Smirnov and likelihood-ratio hypothesis tests, along with logistic-regression-based genomic analyses on the de-identified datasets, we show that CoSMeTIC achieves strong privacy guarantees while maintaining statistical fidelity. Our results suggest that CoSMeTIC provides a scalable and practical alternative for achieving regulatory compliance with rigorous privacy protection in large-scale clinical research.

Duc Thinh Ngo, Arya Rahgoza

Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.

Maria Smith

[Depreciated and replaced by V3] The application-specific clean rebuild has not yet been published; its authoritative theoretical boundary is now the governing V3 branch: After Turing: The Fold Machine - An Exact, Parameter-Free and Machine-Closed Derivation of Classical Computational Science from Smithian Fold Theory; From Fold to Consciousness: An Exact, Zero-Parameter and Machine-Closed Foundational Reconstruction of Consciousness and Cognitive Science from Smithian Fold Theory. The V3 source platform is https://github.com/MettaMazza/ernos-labs-sft-platform. The original DOI, concept DOI, version number and files are preserved for transparent historical provenance; this record must not be presented or cited as current V3 work. v4.0 — the word-scale gap closes within the fold. Rung 5e (pre-registered): the fold-factor mixing law — every context level that holds contributes, weighted 2^level, the engine's own forced halving constant — carries the pure counted engine, with no twin, no prose flood, zero training and zero parameters, past the gradient-trained transformer at word scale: cross-entropy 3.1907 vs the same-day twin's 3.4292 (replicated across two independent anchorings; stacked with the Rung 5d extraction: 3.1344). Both scales of the task gate now belong to the counted engine. Rung 5d's transfer-in verdict is SUPPORTED across three independent arena anchorings in one day. New in the architecture: tool graduation (acts held, values never — a question territory that a tool answered once runs the tool itself thereafter, fresh), recall as regeneration across every memory tier, and judge-independent graduation scoring. End-to-end verification: 36/36. v3.4: Rung 5d, the transfer-in — pre-registered verdict SUPPORTED: the trained twin's dyadically-loud fold content is extracted and installed INTO the counted engine as a counted prior with zero new parameters, closing 55.6/87.9/101.4% of the available gap at k=16/32/64 while the random-truncated null closes 10.1/24.5/56.5%; at half budget the loud shape beats the full twin's own. The word-scale rematch is recorded in full (twin retrained on today's text; decomposition included). Also: judge-independent graduation scoring (boot-discovered pool, cycle-parity alternation), multi-orbit binding (XI-4 in full), recall-is-regeneration (a held experience re-walks its own orbit, never reprinted), the public SOTA table beside the local giants with cited published figures, and one-command replication kits (GPT-2 weights auto-fetch; 13/13, 39/39 proven on a fresh clone). End-to-end verification: 36/36. Full paper v1.1 — supersedes the pre-paper (From One Axiom to Master-Level Chess — and the Law Inside Neural Networks). Built from scratch by one woman, working alone, in under twenty-four accumulated hours: where a score falls short it marks an implementation gap at measurement time, never a limit of the mathematics — the gains between releases are the finding. v1.4 adds the fold eye (vision as exact integer Walsh spectra, self-certified by integer Parseval per image, recognition of seen images with no image model in the loop) and the graduation score (blind head-to-head vs the teacher, tallied per question-territory; the teacher retires as wins cross the majority lock) -- and documents the 2026 convergence: DeepSeek Engram arrives at deterministically-addressed exact memory from the gradient side, and two independent results place the optimal curriculum at p = 1/2, the fold lock. v1.6: the full omnimodal engine (the voice via Kokoro, the fold ear -- sound as Parseval-certified integer Walsh spectra, video composed from frames + sound), speaker-transparent reasoning threads, and 32/32 end-to-end empirical verification of the entire architecture including persistence across process death. v1.7: removal-proof omnimodality, measured -- every supporting model is a teacher with an exit: a sound taught once by the synthesis teacher is re-spoken from the engine's own exact counted record in 0.00s with no model; a sound heard once is recognized natively with no transcriber; 34/34 end-to-end verification. v1.9: zero-model perceptual learning (the human observer -- a novel image learned and re-recognized at share 1.00 with no model in the loop); agentic self-knowledge (the observer reads the engine's own source, measured); the hourly progress instrument with a committed pre-boot birth line; one-tap y/n closure. v2.0 (flight-ready): the full modern-agent toolkit (live web search/fetch, paginated reading, in-file grep -- every call held as a training trace), the 43-domain everything-curriculum under the fold-only law, SOTA 1-1 benching on the public MMLU test split with the newborn baseline committed, generation closure (the Learning Law reaches generate() itself), and 36/36 end-to-end verification. v2.1: the ReAct law (reason-act-observe enforced in-turn; narrated intent without an act is detected and forced), reasoning trained on the observer's NATIVE thinking tokens (STaR-gated) with both minds' full thinking streamed to the user, and document intake (a sent file is reading -- inboxed, counted, persistent). v2.2: the identity stated correctly -- UnisonAI is an OMNI MODEL (language, sight, hearing, speech, and video on one held memory), not a language model; LLMs remain the contrast class only. v3.0: the full-altitude rewrite -- the complete omni model documented at the same depth as the spectral science: thirteen sections, the architecture organ by organ with every measurement, Rung 5c as its own section, the empirical record and its committed birth line, 36/36 end-to-end verification, and the 2026 convergence. This paper is a PROOF of The Smithian Fold Theory of Everything, not the main event: the theory (one axiom, zero free parameters, 1,844 machine-verified forced checks) is at DOI 10.5281/zenodo.21182469 and github.com/MettaMazza/Smithian-Fold-Theory-Of-Everything -- run the prover yourself. The engine: github.com/MettaMazza/UnisonAI. v3.3: the LLM-native presence suite -- the exact registered protocol applied to GPT-2's entire knowledge-storage class: 13/13 tensors, 39/39 checks, unanimous (margins 3.4-79.3x); the flagship claim now rests on the flagship objects, with diffusion/speech models recast as cross-domain breadth. Three connected results and the architecture they force. First, a pre-registered, self-certifying spectral instrument shows trained neural-network weights carry placement-law in the dyadic (Walsh) basis: 18/18 unanimous on validated released models; the law concentrated in transformer expansion projections and token embeddings across three unrelated architectures (up to 230x chance in GPT-2), attention at chance; strictly training-caused (He-initialised controls at 1.0x); surviving 4-bit deployment quantization. A recipe map from 124M to one trillion parameters shows the law tracks training recipe, not scale or architecture — strongest carrier DeepSeek-R1-671B at 43–47x — and loud-recipe weights transform under the fold's transformation group exactly as solved game-theoretic value fields do. Second, the "learned similarity space" is a counted object: word kinship as exact co-occurrence shares reproduces semantic family structure (quark → lepton, neutrino, proton) with zero parameters and zero gradients. Third, UnisonAI: a complete language architecture in which every LLM mechanism — memory, attention, similarity, learning, prediction, generation — is replaced by a machine-verified law of the Smithian Fold Theory, zero trained parameters end to end. On identical held-out text the fold-native engine outperformed its trained transformer twin (cross-entropy 1.289 vs 1.888) after reading the corpus once (26 seconds) against 48,000 gradient readings (21 minutes per seed). Deployed as a live, continuously-learning agent whose teaching loop also runs autonomously: a teacher model asks, judges, and closes the learning law itself, and the engine self-plays against its own held lessons. Negative results reported in full with their scopes. Companion to The Smithian Fold Theory of Everything (DOI: 10.5281/zenodo.21182469; 307 suites, 1,844 forced checks, 0 failures). Engine and records: github.com/MettaMazza/UnisonAI and github.com/MettaMazza/Smithian-Fold-Theory-Of-Everything.

Linda Handayani, Eri P. Wibowo, Avinanta Tarigan, Asep Juarna

No abstract is available for this record.

Pankaj Kumar, Arun K H, Yogesh N, Prakash Babu · 8 authors

The growing dependance on data-based decisionmaking in healthcare has brought attention to the vital importance of secure, privacy-preserving and collaborative learning techniques. Traditional centralized learning approaches in medical data often raise concerns regarding patient privacy data leaks and even regulatory troubles. Federated learning came as a good solution, where it allows model training in different hospitals without sharing the sensitive patient data. However, federated learning has its problems - it can be mislead with fake updates, the model can even be poisoned and it is really hard to trust every participants involved. In this work, we present fed-chain, a secure and scalable framework which brings together federated learning, blockchain and zero-knowledge-proofs(ZKPs) preserving the privacy of patient's data in healthcare. Blockchain here adds decentralized trust, immutability and makes model updates transparent to review while ZKPs helps in proving correctness without leaking personal data. We are implemented this framework for heart disease prediction where multiple hospitals train the model together but the data stays confidential. Our experimental results shown better accuracy, more strength against attacks and even low communication cost compared to other FL setups. Overall, the systems gives a safer approach for working together on healthcare data, allowing hospitals and research centers to generate valuable predictions using these models while keeping the patient data private and safe.

N Mangala, Murtaza Rangwala, S Aishwarya, B Eswara Reddy · 8 authors

Healthcare has become exceptionally sophisticated, as wearables and connected medical devices revolutionize remote patient monitoring, emergency response, medication management, diagnosis, and predictive and prescriptive analytics. Internet of Things and Cloud computing integrated systems (IoT-Cloud) facilitate sensing, automation, and processing for these healthcare applications. While real-time response is crucial for alleviating patient emergencies, protecting patient privacy is paramount in data-driven healthcare. In this paper, we propose a multi-layer IoT, Edge, and Cloud architecture to enhance emergency healthcare response times by distributing tasks based on response criticality and data permanence requirements. We ensure patient privacy through a Differential Privacy framework applied across several machine learning models: K-means, Logistic Regression, Random Forest, and Naive Bayes. We establish a comprehensive threat model identifying three adversary classes and evaluate Laplace, Gaussian, and hybrid noise mechanisms across varying privacy budgets, with supervised algorithms achieving up to 83.6% accuracy. The proposed hybrid Laplace-Gaussian noise mechanism with adaptive budget allocation provides a balanced approach, offering moderate tails and better privacy-utility trade-offs for both low and high-dimension datasets. At the practical threshold of $\varepsilon$=5.0, supervised algorithms achieve 80-81% accuracy while reducing attribute inference attacks by up to 18% and data reconstruction correlation by 70%. We further enhance security through Blockchain integration, which ensures trusted communication through time-stamping, traceability, and immutability for analytics applications. Edge computing demonstrates 8$\times$ latency reduction for emergency scenarios, validating the hierarchical architecture for time-critical operations.

Shrutika Singh, Anton Alyakin, Daniel Alexander Alber, Jaden Stryker · 12 authors

The performance of Large Language Models (LLMs) on multiple-choice question (MCQ) benchmarks is frequently cited as proof of their medical capabilities. We hypothesized that LLM performance on medical MCQs may in part be illusory and driven by factors beyond medical content knowledge and reasoning capabilities. To assess this, we created a novel benchmark of free-response questions with paired MCQs (FreeMedQA). Using this benchmark, we evaluated three state-of-the-art LLMs (GPT-4o, GPT-3.5, and LLama-3-70B-instruct) and found an average absolute deterioration of 39.43% in performance on free-response questions relative to multiple-choice (p = 1.3 * 10 -5 ) which was greater than the human performance decline of 22.29%. To isolate the role of the MCQ format on performance, we performed a masking study, iteratively masking out parts of the question stem. At 100% masking, the average LLM multiple-choice performance was 6.70% greater than random chance (p = 0.002) with one LLM (GPT-4o) obtaining an accuracy of 37.34%. Notably, for all LLMs the free-response performance was near zero. Our results highlight the shortcomings in medical MCQ benchmarks for overestimating the capabilities of LLMs in medicine, and, broadly, the potential for improving both human and machine assessments using LLM-evaluated free-response questions.

Shivani Agarwal, Meenakshi Kandpal, Vishan Kumar Gupta, Shubhani Aggarwal · 5 authors

Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94\% accuracy, 0.90 precision, 0.96 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.

Guodong Yi, Zhihui Wu, Xinyu Zhang, Xiaocui Li

Federated learning (FL) offers a distributed approach for the collaborative training of machine learning models across decentralized clients while safeguarding data privacy. This characteristic makes FL well suited for privacy-sensitive fields such as healthcare and finance. However, addressing the heterogeneity caused by nonindependent and identically distributed (non-IID) data remains a significant challenge for traditional FL methods. To address these issues, the enhancing clustered federated learning with adaptive similarity (AS-CFL) algorithm, which dynamically forms client clusters based on model update similarity and uses a forward-incentive mechanism to improve collaborative training efficiency among similar clients, is proposed in this study. Experimental results on the MNIST and EMNIST datasets reveal that compared with baseline methods such as the CFL, IFCA, and FedAvg models, the AS-CFL algorithm achieves faster convergence—reducing the number of communication rounds by approximately 20%—while maintaining competitive accuracy, demonstrating its effectiveness in heterogeneous FL scenarios.

Dmytro Zakharov, Oleksandr Kurbatov, Artem Sdobnov, Lev Soukhanov · 13 authors

In this report, we compare the performance of our UltraGroth-based zero-knowledge machine learning framework Bionetta to other tools of similar purpose such as EZKL, Lagrange's deep-prove, or zkml. The results show a significant boost in the proving time for custom-crafted neural networks: they can be proven even on mobile devices, enabling numerous client-side proving applications. While our scheme increases the cost of one-time preprocessing steps, such as circuit compilation and generating trusted setup, our approach is, to the best of our knowledge, the only one that is deployable on the native EVM smart contracts without overwhelming proof size and verification overheads.

Lilia Tightiz, Abdulkhamidov Akbarjon Sobitkhon Ughli, Joon Yoo

This paper presents a novel health data analysis platform for improved individualized risk forecasting of permanent pacemaker implantation (PPI) following transcatheter aortic valve replacement (TAVR) procedures. Specifically, we introduce XGBoost-federated adaptive interpolation transfer learning (XG-FedAIT)—a platform that integrates heterogeneous hospital data sets via adaptive output-level interpolation and performance-weighted model ensembling. This approach facilitates federated learning across institutions with different feature spaces and prediction targets, such as time-to-event and binary models, eliminating structural and semantic mismatches prevalent in regular federated transfer learning. To ensure secure, privacy-preserving, and general data protection regulation (GDPR)-compliant data exchange, we propose a dual-chain blockchain architecture integrating proof of authority (PoA), zero-knowledge proofs (ZKPs), and chain-specific smart contracts, and off-chain encrypted storage through Filecoin. Experimental evaluation proves that the PrimaryChain handles over 300 tx/s with a median latency of 500 ms, and the SecondaryChain offers 99.8% data availability and decentralized access control. The system is scalable to handle up to 2,500 transactions/hour, and the federated learning pipeline classifies PPI risk with an F1-score of 0.85 and AUROC of 0.91. These results support the effectiveness of our system in delivering real-time, regulation-compliant, and clinically actionable cardiac care in distributed environments.

Samia Sayed, Muammar Shahrear Famous, Rashed Mazumder, Risala Tasin Khan · 8 authors

Blockchain is an emerging technology that is being used to create innovative solutions in many areas, including healthcare. Nowadays healthcare systems face challenges, especially with security, trust, and remote data access. As patient records are digitized and medical systems become more interconnected, the risk of sensitive data being exposed to cyber threats has grown. In this evolving time for healthcare, it is important to find a balance between the advantages of new technology and the protection of patient information. The combination of blockchain–InterPlanetary File System technology and conventional electronic health record (EHR) management has the potential to transform the healthcare industry by enhancing data security, interoperability, and transparency. However, a major issue that still exists in traditional healthcare systems is the continuous problem of remote data unavailability. This research examines practical methods for safely accessing patient data from any location at any time, with a special focus on IPFS servers and blockchain technology in addition to group signature encryption. Essential processes like maintaining the confidentiality of medical records and safe data transmission could be made easier by these technologies. Our proposed framework enables secure, remote access to patient data while preserving accessibility, integrity, and confidentiality using Ethereum blockchain, IPFS, and group signature encryption, demonstrating hospital-scale scalability and efficiency. Experiments show predictable throughput reduction with file size (200 → 90 tps), controlled latency growth (90 → 200 ms), and moderate gas increase (85k → 98k), confirming scalability and efficiency under varying healthcare workloads. Unlike prior blockchain–IPFS–encryption frameworks, our system demonstrates hospital-scale feasibility through the practical integration of group signatures, hierarchical key management, and off-chain erasure compliance. This design enables scalable anonymous authentication, immediate blocking of compromised credentials, and efficient key rotation without costly re-encryption.