Publications

2026

• Pseudonym Certificate Revocation in V2X: Liability, Scalability and Latency. A Quantitative Analysis and a Roadmap toward a Standardizable Solution
  
  • Grund Jean-Jacques
  • Khatoun Rida
  • Pujolle Guy
  • Serhrouchni Ahmed
  , 2026. <div><p>The security of V2X communications relies on pseudonym certificates that sign a very large volume of cooperative messages (CAM, DENM, BSM, SRM) at rates of up to 10 Hz, in environments where connectivity is intermittent. Under these conditions, the revocation of these certificates is the most challenging link of the trust chain: it couples three frequently antagonistic requirements -liability (the ability to attribute and rapidly exclude a compromised device without breaking conditional privacy), scalability (the effects of pseudonym inflation and of the cumulative volume of revocations), and latency (a budget of a few tens to a few hundreds of milliseconds per application decision). This paper provides a quantitative analysis of the state of the art, structured along the three stages of the revocation process (resolution, distribution, use). We formalize six requirements R1-R6 and a homogeneous sizing model, and we show, using explicit European-scale deployment figures, that neither classical X.509 PKI nor any individual family of existing schemes (CRL and its optimizations, probabilistic filters, SCMS linkage, short-lived certificates, Merkle structures, online and symmetric approaches, group signatures, distributed ledgers) simultaneously satisfies the six requirements. We identify eight structural gaps and translate them into a roadmap of eight objectives O1-O8. This paper constitutes Part I of a two-part contribution: it establishes the analytical foundation -requirements, quantitative sizing, structural gaps, and a specification-level roadmap -while the design of a compliant mechanism, its security analysis, and its experimental evaluation are presented in a dedicated companion paper (Part II).</p></div>
• Structural analysis of Petri nets
  
  • Memmi Gérard
  • Barkaoui Kamel
  • Ma Ziyue
  • Mahulea Cristian
  Discrete Event Dynamic Systems, Springer Verlag, 2026, 36 (1), pp.31. This tutorial paper provides a comprehensive overview of structural analysis techniques for Petri Nets (PNs). We recall the fundamental concepts, definitions, and notations, and highlight the role of structural properties in the analysis and verification of complex Discrete-Event Systems (DESs). Beyond classical tools such as invariants, semiflows, traps, and siphons, special attention is devoted to the notions of home spaces and basis reachability graphs, which offer compact and effective alternatives to exhaustive state-space exploration. Real-world examples, including applications in telecommunications, illustrate the practical relevance and applicability of these methods. The paper aims to serve both as a reference for researchers and as an accessible entry point for graduate students interested in Petri net theory and applications. (10.1007/s10626-026-00453-w)
  DOI : 10.1007/s10626-026-00453-w
• Not In My Git Yard: Catching Backdoors at Commit and Release Time
  
  • Kokkonis Dimitri
  • Marcozzi Michaël
  • Zacchiroli Stefano
  , 2026, pp.273 - 284. Code-level backdoors-stealthy code changes that grant hidden privileges via secret triggers-pose a persistent threat to opensource software. Known attempts to inject such backdoors into widely used projects through malicious commits, tampered release packages, or compromised third-party dependencies, were stopped only by luck and manual review. Existing Continuous Integration (CI) pipelines cannot detect these attacks, and downstream binary analysis tools require substantial manual effort. In this work, we present Lily, an automated approach that strengthens open-source development and release processes against backdoor injection. Lily integrates a backdoor detection mechanism into (1) CI pipelines to block malicious commits, and (2) release vetting workflows to prevent tampered releases or compromised dependencies from entering large ecosystems, such as Linux distributions. Lily offers two key contributions. First, it enhances CI-compatible fuzzing with the capability to detect triggers of suspicious behavior based on historical and current software executions. This enables fast, precise backdoor detection suitable for both CI and update validation workflows. Second, it combines code change analysis with fuzzing data to precisely point maintainers to backdoor-revealing code regions, even when release updates modify millions of lines of code. We also outline five strategies attackers could use to evade Lily, and evaluate corresponding defenses. Our experiments across hundreds of benign and backdoored commits and releases show that Lily achieves high detection accuracy with low false alarm rates, reliably identifies malicious code, resists adversarial attempts, and would have prevented real-world backdoor incidents. (10.1145/3832783.3834352)
  DOI : 10.1145/3832783.3834352
• Physical Layer Security with Frequency-Hopping and Finite-Alphabet Inputs
  
  • Leroy Clément
  • Arbi Tarak
  • Geller Benoit
  • Rioul Olivier
  , 2026. <div><p>This paper investigates the physical layer security of frequency-hopping (FH) transmission schemes when the hopping sequence is publicly known. We consider a single-antenna transmitter communicating with a legitimate receiver over a channel estimated with a known error distribution, in the presence of a passive eavesdropper whose channel statistics are available at the transmitter. We show that, when the number of hopping frequencies is sufficiently large, the instantaneous channel fluctuations induced by FH transmissions can be effectively averaged out, and the secrecy performance is accurately predicted by the ergodic secrecy rate (ESR). The ESR is maximized by selecting the optimal modulation order from a set of admissible finite constellations. We derive a closed-form condition on the optimal modulation order, which only depends on the tail probabilities of the legitimate and eavesdropper signal-to-noise ratio (SNR) distributions, and we propose an efficient algorithm for its computation. In particular, we demonstrate that a positive secrecy rate can be achieved even when the eavesdropper has a higher average SNR than the legitimate receiver, provided that the spread of the eavesdropper SNR distribution is sufficiently large. Numerical results validate the proposed framework under a variety of channel models.</p></div>
• Picturing general quantum subsystems
  
  • Mestoudjian Octave
  • Wilson Matt
  • Vanrietvelde Augustin
  • Arrighi Pablo
  , 2026. We extend the usual process-theoretic view on locality and causality in subsystems (based on the tensor product case) to general quantum systems (i.e. possibly non-factor, finite-dimensional von Neumann algebras). To do so, we introduce a primitive notion of splitting maps within dagger symmetric monoidal categories. Splitting maps give rise to subsystems that admit comparison via a preorder called comprehension, and support an adaptation of the usual categorical trace. We show that the comprehension preorder precisely captures the inclusion partial order between von Neumann algebras, and that the splitting map trace captures the natural notion of von Neumann algebra trace. As a consequence of the development of these diagrammatic tools, we prove that the known equivalence between semi-causality and semi-localisability for factor subsystems extends to all (including non-factor) subsystems.
• Specifying the operational meaning of quantum reference frames
  
  • Vanrietvelde Augustin
  , 2026. In their strongest usage, quantum reference frames have been described as referring to "the measurements performed by a superposed lab", "the perspective of a quantum particle", "the point of view of a superposed observer", etc. While exciting, these operational proposals have remained brief and ambiguous, leading to misinterpretations and criticism. Here, we provide a detailed specification and defense of the notion of a position-superposed lab or observer. We argue that this requires no exotic claims about quantum physics and raises no greater interpretive difficulty than ordinary quantum measurements. We then derive several consequences of taking this operational meaning seriously. We stress that the position-superposed observers that define quantum references frames are different from, and considerably less problematic than, the outcome-superposed observers considered in Wigners' friend scenarios. In particular, we show that outcomes obtained by a position-superposed observer may (without decohering the superposition) be broadcast to a well-localised one, in contrast with Wigner's friend scenarios, which require the outcomes to remain internal to the system at hand. Finally, we defend the possibility to roleplay a quantum reference frame from a classical reference frame.
• RISCGuard: RISC-V Static Analysis Framework for Detecting Microarchitectural Vulnerabilities
  
  • Khan Mahreen
  • Mushtaq Maria
  • Pacalet Renaud
  • Apvrille Ludovic
  , 2026. <div><p>The proliferation of RISC-V processors in security-critical applications has raised concerns about side-channel vulnerabilities, particularly those arising from speculative execution and cache timing attacks. While software-based mitigation strategies exist, automated detection of vulnerable code patterns remains challenging. This paper presents RISCGuard, a novel static analysis framework specifically designed to identify side-channel vulnerabilities in RISC-V assembly code. RISC-Guard employs sophisticated pattern matching, data-flow analysis, and taint tracking to detect ten distinct vulnerability classes, including Spectre variants (V1, V2, V4), cache timing attacks (Flush+Reload, Prime+Probe), cache conflict patterns, timing side-channels, password timing vulnerabilities, secret-dependent control flow, and unaligned memory access patterns. We evaluate RISCGuard on a comprehensive dataset comprising 100 benign sequences, 125 known vulnerable patterns, and 100,000 randomly generated instruction sequences. Our experimental results demonstrate an overall accuracy of 99.6% across all test cases, with low false-positive and false-negative rates. The framework generates detailed vulnerability reports that include risk assessments ranging from critical to low, confidence scores averaging 0.89, and mitigation recommendations. Our paper addresses a crucial gap in RISC-V security tooling and provides developers with an automated solution for identifying and mitigating side-channel vulnerabilities before deployment.</p></div>
• SPS: Simulate. Predict. Secure; Pre-Silicon Validation of Embedded Kernels via ML-Enhanced Cycle-Accurate Simulation and Anomaly Detection
  
  • Awais Muhammad
  • Mushtaq Maria
  • Naviner Lirida
  • Haj Jawad
  • Bruguier Florent
  , 2026, 14th. Pre-silicon validation of embedded processors demands simulation frameworks that simultaneously capture microarchitectural timing, peripheral behavior, and firmware interactions, requirements that functional emulators and analytical models fail to meet. This paper introduces SPS (Simulate. Predict. Secure.), a gem5-based framework extended with embedded kernel models, memory hierarchies, and peripheral co-simulation, coupled with machine learning to accelerate design-space exploration and enable microarchitectural anomaly detection. Representative kernels spanning signal processing, control, communication, and lightweight security workloads are executed in Syscall Emulation mode to collect fine-grained statistics including cache activity, bus contention, interrupt latency, and execution cycles. These features train surrogate ML models that reduce exploration time by up to 10× while recovering over 93% of the Pareto front, with energy and performance prediction errors below 3.2% and 2.8% respectively. The framework further incorporates an anomaly detection layer operating on gem5 performance counters, achieving AUC-ROC ≥ 0.89 across six fault classes including interrupt storms, cache thrashing, memory leaks, and security breaches. Experimental results confirm that SPS delivers efficient exploration, accurate prediction, and robust fault detection, establishing a scalable pre-silicon methodology for energy-aware and secure embedded processor design.
• Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation
  
  • Lim Gionnieve
  • Tan Bryan Cheng Zhengyu
  • Sim Kellie Yu Hui
  • Shi Weiyan
  • Chew Ming Hui
  • Hee Ming Shan
  • Lee Roy Ka-Wei
  • Perrault Simon
  • Choo Kenny Tsu Wei
  , 2026. The emergence of Large Language Models (LLMs) presents a dual challenge in the fight against disinformation. These powerful tools, capable of generating human-like text at scale, can be weaponised to produce sophisticated disinformation, yet they also hold promise for enhancing mitigation strategies. This paper investigates the complex dynamics between LLMs and disinformation in small, localised settings through a communication game based on online forums, inspired by Werewolf, with 25 participants. We analyse how Disinformers, Moderators, and Users leverage LLMs to advance their goals, revealing both the potential for misuse and combating disinformation. Our findings highlight the varying uses of LLMs depending on the participants' roles and strategies, underscoring the importance of understanding their effectiveness in this context. We conclude by discussing implications for future LLM development and online platform design, advocating for a balanced approach that empowers users and fosters trust while mitigating the risks of LLM-assisted disinformation. (10.1145/3817008)
  DOI : 10.1145/3817008
• Robustness and optimization of NOON-state interferometry
  
  • Dalidet Romain
  • Martin Anthony
  • Bellando Louis
  • Bellec Matthieu
  • Fabre Nicolas
  • Tanzilli Sébastien
  • Labonté Laurent
  Physical Review A, American Physical Society, 2026, 114 (4), pp.043709. Quantum-enhanced interferometry is often discussed in terms of ideal resources and asymptotic scalings, whereas in practice its performance is set by a delicate interplay between losses, state imbalance, and photon number. We address this interplay in a folded Franson interferometer fed with partially entangled NOON states, treating asymmetric losses and tunable input imbalance on equal footing. From exact detection probabilities we obtain closed-form expressions for the fringe visibility and the Fisher information, and show that these two figures of merit respond very differently to imperfections. In particular, we demonstrate that perfect interference contrast can always be recovered by compensating loss asymmetry with an appropriate input imbalance, while the Fisher information generally peaks at a distinct operating point, reflecting the irreducible trade-off between coherence restoration and signal attenuation. By determining the exact optima and benchmarking against single-photon strategies, we identify the critical loss and minimum entanglement required to maintain a genuine quantum advantage over optimized single-photon strategies under identical loss conditions, and establish their scaling with the photon number N. Beyond delineating the fundamental trade-offs between loss, entanglement, and sensitivity, this work establishes a comprehensive theoretical framework that both underpins and extends the experimental demonstration of quantum advantage we have reported previously, providing a unified description of the relevant operating regimes. (10.1103/lrfy-khr5)
  DOI : 10.1103/lrfy-khr5
• Did You Forkget It? Detecting One-Day Vulnerabilities in Open-source Forks With Global History Analysis
  
  • Lefeuvre Romain
  • Reux Charly
  • Zacchiroli Stefano
  • Barais Olivier
  • Combemale Benoit
  , 2026. Tracking vulnerabilities inherited from third-party open-source software is a well-known challenge, often addressed by tracing the threads of dependency information. However, vulnerabilities can also propagate through forking: a code repository forked after the introduction of a vulnerability, but before it is patched, may remain vulnerable long after the vulnerability has been fixed in the initial repository. History analysis approaches are used to track vulnerable software versions at scale. However, such approaches fail to track vulnerabilities in forks, leaving fork maintainers to identify them manually. This paper presents a global history analysis approach to help software developers identify one-day (known but unpatched) vulnerabilities in forked repositories. Leveraging the global graph of public code, as captured by the Software Heritage archive, our approach propagates vulnerability information at the commit level and performs automated impact analysis. Starting from 7162 repositories with vulnerable commits listed in OSV, we propagate vulnerability information to 2.2 million forks. We evaluate our approach by filtering forks with significant user bases whose latest commit is still potentially vulnerable, manually auditing the code, and contacting maintainers for confirmation and responsible disclosure. This process identified 135 high-severity one-day vulnerabilities, achieving a precision of 0.69, with 9 confirmed by maintainers.
• Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach
  
  • Ngo Anh
  • Rollet Nicolas
  • Pelachaud Catherine
  • Clavel Chloé
  , 2026, pp.873 - 882. Other-initiated Self-repair, or in short Other-initiated Repair (OIR), is an essential mechanism in conversational interaction, whereby a recipient signals a problem in speaking, hearing, or understanding, prompting the previous speaker to resolve it. In the case of conversational agents, it is essential to accurately identify these repair initiation strategies to address communication breakdowns efficiently. While conversational analysis studies have shown that OIR initiation is accompanied by both verbal and non-verbal signals such as gaze shifts, facial expressions, body postures, and hand gestures, existing computational approaches rely mainly on text and audio. This paper introduces a novel multimodal model for OIR detection and classification, incorporating a set of visual features drawn from conversation analysis. We evaluate our approach on two corpora with distinct languages and interaction settings. Results demonstrate that visual information consistently improves performance over text and audio baselines, and provide insights into cross-modal feature contributions across two corpora. (10.1145/3776574.3831200)
  DOI : 10.1145/3776574.3831200
• A Methodology to Compare Real and LLM-Simulated Multimodal Interactions: The Case of Gender Bias
  
  • Etienne Elodie
  • Ochs Magalie
  • Loubes Jean-Michel
  • Clavel Chloé
  , 2026, pp.462 - 471. Large Language Models (LLMs) are increasingly used to generate multimodal data for building corpora or simulating synthetic behaviours. A key challenge remains the evaluation of generated data. Comparison with real multimodal human interactions may help address this issue, but unified representations and evaluation frameworks are still lacking. In this article, we introduce MAMBI (Multimodal Annotation and Measurements for Bias in Interactions), an open-source tool designed to facilitate systematic comparisons between real and LLM-simulated multimodal human interactions. For this purpose, a standardised enriched multimodal transcript format is proposed, providing a common representation of verbal, prosodic, and non-verbal behaviours. This representation is obtained through an automatic annotation pipeline that transforms raw audio-visual recordings into structured narrative transcripts by combining speech transcript, segmentation, prosodic and facial feature extraction. The pipeline is applied on multiple multimodal corpora, demonstrating its portability across diverse interaction settings and different numbers of participants. Based on this enriched multimodal transcript, a framework is introduced to assess the statistical consistency between real and generated data, focusing on distributional similarity and correlation structure preservation in the prosodic, interactional dynamics, and facial expressions features, with a particular attention on the bias analysis to quantify group-related disparities. As a use case, we present in this article an analysis of \textit{gender} bias on a large \textit{dyadic} interaction corpus. The results show that enforcing distributional constraints substantially improves alignment with real data, whereas structural consistency depends more unevenly on the prompting strategy and is not systematically maximized by correlation-oriented prompting alone. However, all generations amplify gender-related biases, especially in prosodic cues such as pitch and speech rate, and in facial behaviours such as smiling, blinking, and raised cheeks. Overall, the proposed tool facilitates the generation, evaluation, and critical analysis of multimodal interactions, contributing to bridging the gap between real and LLM-simulated data. (10.1145/3776574.3831157)
  DOI : 10.1145/3776574.3831157
• Toward Low-Barrier Participatory Mapping Workshops: Designing Marker-Based Tangible Interactions for Projected Tabletops
  
  • Masoudifard Arsalan
  • Bagheri Nasim
  • Lotfi Soheil
  • Huron Samuel
  • Mavros Panagiotis
  , 2026, pp.1-8. Participatory mapping workshops bring local knowledge and needs into urban planning, but face a trade-off between accessibility and digital capability. Pen-and-paper methods lack automatic data capture and real-time visualization, while digital tangible tabletops require specialized, expensive hardware. Off-the-shelf projectors and cameras can turn ordinary surfaces into interactive displays, but existing implementations rely on detecting hand gestures, which are unreliable under projector lighting. Instead, printed fiducial markers offer robust tracking, but are inherently passive and lack established user-interaction techniques. To bridge this gap, we focus on object manipulation, rather than hand-tracking, using cardboard objects with fiducial markers. We test four new triggering mechanisms supporting a range of map interactions in a browser-based prototype, developed iteratively through three workshops (N=12), using participant feedback to improve reliability, expressiveness, and collaborative mapping. Our findings suggest this approach’s viability and open up directions for further work on tangible interaction in low-barrier participatory mapping. (10.1145/3821402.3830147)
  DOI : 10.1145/3821402.3830147
• Self-phase modulation in high-resolution DAS: impact of high-peak-power Gaussian pulses
  
  • Chiabaut Anaïs
  • Gabet Renaud
  • Arpison Guillaume
  • Peigné Arnaud
  Optics Express, Optical Society of America - OSA Publishing, 2026, 34 (20), pp.38533. Modulation instability (MI) is a well-known limit for distributed fiber sensors. However, self-phase modulation (SPM) is rarely addressed as a standalone constraint in distributed acoustic sensing (DAS). This study demonstrates, through modeling and experiments, that SPM-induced spectral broadening causes significant backscattered signal losses and increased phase noise. These effects are particularly critical when using high-power, short Gaussian pulses commonly used to extend the sensing range. We highlight the predominant role of the detection bandwidth in these excess losses, proving that SPM is a limiting factor independent of MI for high-resolution nonlinear ϕ -OTDR measurements. (10.1364/OE.606361)
  DOI : 10.1364/OE.606361
• Temporal Prediction of RF-EMF Exposure Using Surrogate Modeling with Environment-Based Clustering
  
  • Lagouanelle Paul
  • Shanshan Wang
  • Yukun Liu
  • Yarui Zhang
  • Joe Wiart
  URSI Radio Science Letters, International Union of Radio Science (URSI), 2026, 8. (10.46620/26-0102)
  DOI : 10.46620/26-0102
• Art in Humanity’s Code
  
  • Baudry Benoit
  • Gamage Yogya
  • Fernandez Nadia Gonzalez
  • Mk Lena
  • Mendieta Roxana Pena
  • Pinter Rafaela Souza
  • Zacchiroli Stefano
  IEEE Transactions on Software Engineering, Institute of Electrical and Electronics Engineers, 2026, pp.1-17. Artist-led open-source libraries such as Processing or openFrameworks have had a major impact on artists and designers who use code as a creative medium. In this work, we conduct the first large-scale empirical study of public code repositories that use these libraries. Our study dives into 1,613,571 code repositories collected from the Software Heritage archive. Blending quantitative and qualitative methods, we investigate the diversity of practices and practitioners regarding code hosting, geographical distribution, and the characteristics and purposes of code-based creative works. Key findings include evidence of the worldwide practice of generative art and creative coding, as well as the adoption of these practices in both education and across creative industries. We illustrate these findings with concrete examples of repositories and contributor profiles around the globe, spanning the spectrum of code-based art, from visual to sound art. These results lay the groundwork for educators, researchers, and artists who investigate code and creative practices to sustain diversity in the construction of our digital world. (10.1109/TSE.2026.3742130)
  DOI : 10.1109/TSE.2026.3742130
• How timing and mode of selection shape ancestral genetic contributions
  
  • Mardomingo-Sanz Juan
  • Tran-Thanh Raphaël
  • Coron Camille
  • Abu Awad Diala
  , 2026. We examine a population that evolves according to a biparental Moran model with two distinct types of individuals. Each individual’s type is determined by the allele they carry at one biallelic locus, which is transmitted in a Mendelian way. This type influences the individual’s mating preferences. We investigate two specific mating patterns: (i) where the type determines the level of attractiveness, and (ii) where the type dictates the level of homogamous choosiness. In both scenarios, one type has an advantage over the other. Assuming an initial proportion b of individuals are of the advantaged type, we give an explicit formula for the asymptotic proportion of the population’s genome that originates from these advantaged ancestors under an infinite population size approximation. Our results enable a comparison of the relative strengths of homogamous choosiness, attractiveness, and viability selection in terms of genome transmission, and prove notably that viability selection is always more efficient than both forms of reproductive selection.
• Microstructure characterization of self-healing vitrimers via matrix assisted laser desorption/ionization (MALDI) and thermal desorption/pyrolysis direct analysis in real time (TDPy-DART) mass spectrometry (MS) techniques
  
  • Bochenek Calum
  • Molina Luciana Rivera
  • Edwards Jack
  • Arntz Tyler
  • Williams-Pavlantos Kayla
  • Eagan James
  • Wesdemiotis Chrys
  Polymer, Elsevier, 2026, 363, pp.130525. (10.1016/j.polymer.2026.130525)
  DOI : 10.1016/j.polymer.2026.130525
• Feature Toggle Dynamics in Large-Scale Systems: Prevalence, Growth, Lifespan, and Benchmarking
  
  • Tërnava Xhevahire
  , 2026. <div><p>Feature toggles enable gradual rollouts and experimentation in software systems, yet often persist beyond their intended lifecycle, accumulating as technical debt. Prior research has examined feature toggle interactions and complexity, but no longitudinal study has quantified how toggles evolve over time across different organizational contexts. We analyse over 4,000 toggle events in Kubernetes (10 MLoC, 8.5 years) and GitLab (5 MLoC, 5 years). We find that feature toggle removals lags behind additions in both systems (by roughly 35% and 13%, respectively), leading to growing toggle inventories. Their lifespan patterns also differ notably, with Kubernetes toggles lasting a median of 734 days versus 185 in GitLab. Then, some feature toggles (1.33% and 0.73%, respectively) exceed all previously observed removal durations, becoming de facto permanent. Building on these findings, we propose a benchmarking framework with five key metrics and their empirically derived threshold zones, enabling practitioners to assess and compare toggle management practices across projects. All scripts and data are publicly available.</p></div> (10.5281/zenodo.18773811)
  DOI : 10.5281/zenodo.18773811
• Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
  
  • Tërnava Xhevahire
  , 2026. In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural language prompt, but what happens to the variability that traditional software engineering carefully builds into code? To answer this question, we conducted an exploratory analysis on 10 vibe coded C/C++ projects, which suggests that there is near zero in-artifact variability, i.e., at compile- and runtime. All variability decisions are resolved at a single new binding time, generation time, the moment the LLM produces the source code. Rather than treating this as a defect to fix, we propose Variability by Regeneration (VbR), to our knowledge the first product line approach in which the LLM acts as the derivation engine, generating a dedicated, free of dead code binary for each variant from a declarative specification, while a variant dispatcher transparently routes user requests to the matching binary. We formalise VbR, contrast it with classical SPL derivation, and demonstrate its full pipeline on a wc product family. For SPL engineering, variability in AI-generated software belongs in the specification, not in the code. (10.5281/zenodo.20730698)
  DOI : 10.5281/zenodo.20730698
• Accessible Quantum Correlations Under Complexity Constraints
  
  • Yángüez Álvaro
  • Avidan Noam
  • Kochanowski Jan
  • Hahn Thomas A
  , 2026. Quantum systems may contain underlying correlations which are inaccessible to computationally bounded observers. We capture this distinction through a framework that analyses bipartite states only using efficiently implementable quantum channels. This leads to a complexity-constrained max-divergence and a corresponding computational min-entropy. The latter quantity recovers the standard operational meaning of the conditional min-entropy: in the fully quantum case, it quantifies the largest overlap with a maximally entangled state attainable via efficient operations on the conditional subsystem. For classical-quantum states, it further reduces to the optimal guessing probability of a computationally bounded observer with access to side information. Lastly, in the absence of side information, the computational min-entropy simplifies to a computational notion of the operator norm. We then establish strong separations between the information-theoretic and complexity-constrained notions of min-entropy. For pure states, there exist highly entangled families of states with extremal min-entropy whose efficiently accessible entanglement in terms of computational min-entropy is exponentially suppressed. For mixed states, the separation is even sharper: the information-theoretic conditional min-entropy can be highly negative while the complexity-constrained quantity remains nearly maximal. Overall, our results demonstrate that computational constraints can fundamentally limit the quantum correlations that are observable in practice.
• Counterfactual Contrastive Analysis
  
  • He Yunlong
  • Gori Pietro
  , 2026, 16882, pp.132–142. Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the classifier's prediction. Existing VCE methods are inherently classifier-dependent and therefore susceptible to classifier biases and failure modes, such as sensitivity to shortcut features and calibration errors. In this paper, we propose a classifier-free approach for visual counterfactual generation based on Contrastive Analysis (CA). Given two datasets corresponding to different classes (e.g., healthy and patients), we disentangle the generative factors that are common across the two datasets from those that are salient to each dataset, and generate counterfactual images by swapping only the salient factors. By operating directly on data distributions rather than decision boundaries, our method provides model-agnostic VCEs that are less sensitive to classifier biases. Our approach leverages the high-quality synthesis and wellstructured latent space of StyleGAN2. We use the feature space F , instead than the usual W -space, to improve detail preservation. Unlike conventional CA approaches, which typically assume salient factors in only one dataset, we introduce an adapted framework and loss functions for VCE that allow multiple salient factors in each dataset. We evaluate our method on three medical imaging datasets and demonstrate superior counterfactual generation quality compared to existing approaches. (10.1007/978-3-032-38079-1_13)
  DOI : 10.1007/978-3-032-38079-1_13
• One-year progression of CT emphysema subtypes predict lung function decline: SPIROMICS
  
  • Hermann Emilia
  • Hoffman Eric
  • Angelini Elsa
  • Barjaktarevic Igor
  • Bon Jessica
  • Comellas Alejandro
  • Cooper Christopher
  • Couper David
  • Curtis Jeffrey
  • Criner Gerard
  • Wells J Michael
  • Paine Robert
  • Krishnan Jerry
  • Labaki Wassim
  • Laine Andrew
  • Lynch David
  • Han Meilan
  • Hansel Nadia
  • Martinez Fernando
  • Ortega Victor
  • Smith Benjamin
  • Sun Yifei
  • Woodruff Prescott
  • Barr R Graham
  American Journal of Respiratory and Critical Care Medicine, American Thoracic Society, 2026. Abstract Rationale Intermediate endpoints that predict lung function decline are needed to improve the efficiency of clinical trials in chronic obstructive pulmonary disease (COPD). Objectives To test if one-year progression of quantitative computed tomography (QCT) measures predicts subsequent FEV₁ decline. Methods SPIROMICS recruited individuals with ≥ 20 pack-years smoking history with or without COPD and nonsmoking controls who underwent four annual and a later fifth visit. We analyzed chest CT scans at visits one and two for machine-learned CT emphysema subtypes (combined bronchitic-apical emphysema [CBaE], diffuse emphysema) and standard QCT measures of emphysema (percent emphysema-950HU, 15th percentile HU, volume-adjusted lung density), airways, functional small airways, hyperinflation, parenchymal texture and vasculature. Linear mixed-effects models evaluated associations between one-year QCT measure changes and FEV₁ decline from visits two through five, adjusting for demographics, site, enrollment group, baseline QCT value, and time-varying anthropometrics and smoking. Measurements and Main Results Among 880 participants (43% mild/moderate COPD, 17% severe COPD, 29% smoking controls, 11% nonsmoking controls), FEV₁ declined -30.4mL/year (95% CI: -34.5, -26.3). A standard deviation (SD) one-year increase in CBaE and diffuse emphysema predicted an accelerated decline in FEV1 of − 4.2 mL/year (95% CI: −8.3, −0.2) and −6.2 mL/year (95% CI: −10.7, −1.8), respectively. Changes in standard QCT emphysema measures also predicted change in FEV1 decline, but only CBaE and diffuse emphysema remained independently predictive of accelerated FEV1 decline when all were considered together. Conclusions One-year progression of CT emphysema subtypes predicted accelerated FEV₁ decline, supporting their potential use as intermediate endpoints in COPD trials. (10.1093/ajrccm/aamag497)
  DOI : 10.1093/ajrccm/aamag497
• Probabilistic Obstruction Temporal Logic: a Probabilistic Logic to Reason about Dynamic Models
  
  • Leneutre Jean
  • Malvone Vadim
  • Ortiz James
  , 2026. In this paper, we propose a novel formalism called Probabilistic Obstruction Temporal Logic (POTL), which extends Obstruction Logic (OL) by incorporating probabilistic elements. POTL provides a robust framework for reasoning about the probabilistic behaviors and strategic interactions between attackers and defenders in environments where probabilistic events influence outcomes. We explore the model checking complexity of POTL and demonstrate that it is not higher than that of Probabilistic Computation Tree Logic (PCTL), making it both expressive and computationally feasible for cybersecurity and privacy applications.