Papers

In the torn paper channel, a codeword is cut at random locations, and the resulting error-free fragments are delivered to the decoder as an unordered multiset. Although the capacity of this channel can be achieved using random code, decoding such codes generally requires exponential time. The interleaved-pilot construction of Shomorony and Vahid embeds a De Bruijn sequence among the symbols of a shifted erasure code and aligns only fragments that are sufficiently long through global statistical uniqueness. A subsequent local-alignment scheme by Liu and Raviv employs run-length-limited constraints and exclusive all-zero markers to identify pilot positions from local structure, substantially reducing the minimum fragment length that can be aligned. We further improve the method of Liu and Raviv by replacing its fixed pilot sequence with a multilevel successive local alignment and pilot-recycling procedure. In Liu and Raviv, the pilot sequence is chosen once and must simultaneously balance the length of the pilot sequence against the ability to align short fragments. Our construction removes this limitation by reusing pilot sequences across successive decoding levels. A pilot sequence with an independent random linear code is first used to align and decode the longest fragments. The information recovered at this stage is then recycled as a larger pilot sequence for the next stage.This process is repeated over multiple levels, so that progressively shorter fragments are recovered while the length of the pilot sequence remains small. Our construction depends on choosing a series of random linear codes, and we show that for any $\varepsilon>0$, there exists a choice of such codes which attains rate of at least $\varepsilon$ below the capacity, with high probability as the block length goes to infinity. Therefore, our construction achieves the capacity of the torn-paper channel.

From horizon detection to fibre structures in X-ray imaging, many vision tasks recover lines via peak detection in Hough space $H=S^1\times\mathbb{R}$, the domain of orientation-offset pairs $(\theta,\rho)$. Differentiable pipelines extract coordinates via soft-argmax, a probability-weighted average that is only meaningful in a globally linear space. However, $(\theta,\rho)$ and $(\theta+\pi,-\rho)$ describe the same undirected line, so $H$ double-covers the space of undirected lines $H/\mathbb{Z}_2$: a Möbius strip, obtained by identifying each pair under $\mathbb{Z}_2$ action. Soft-argmax operates on the cover $H$, but since $H/\mathbb{Z}_2$ admits no linear structure, it tears geometrically adjacent lines apart. Thus we need a $\mathbb{Z}_2$-invariant embedding of lines into a linear space, on which soft-argmax is well-defined. We achieve this by parametrising lines via unit-norm homogeneous vectors $\ell=(1+\rho^2)^{-1/2}(\cos\theta,\sin\theta,-\rho)^{\top}\in\mathbb{R}^3$ and applying the Veronese map $v_2(\ell)=\ell\ell^{\top}$ that satisfies $v_2(\ell)=v_2(-\ell)$. This descends continuously to an embedding of the quotient $H/\mathbb{Z}_2$ into the linear space $\mathrm{Sym}^2(\mathbb{R}^3)$, where the antipodal ambiguity vanishes. Line extraction becomes a barycentre in $\mathrm{Sym}^2(\mathbb{R}^3)$, projected back via its leading eigenvector. We validate our Veronese soft-argmax in a Hough transform-based network across all resolvable lines, confirming uniform and seam-free recovery. We further derive that the $L_2$-loss on isometrically weighted Veronese embeddings equals the squared chordal distance between lines in projective space, enabling a geometrically precise training objective.

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an attacker who keeps adapting or finds another way in. We determine what each reported result implies for that question, allowing results from different safeguard families to be compared under one deployment criterion. The evidence requirements are strongly asymmetric. One attack that obtains harmful help from the deployed service suffices to establish that such help remains, and such attacks appear repeatedly in the coded record. Establishing that little remains cannot follow from the safeguard's own numbers alone; it also requires evidence about what the surrounding system still allows after the safeguard performs its local function. Such evidence is supported or derived in only a small minority of the depth-coded claims, and one such claim bounds its scoped residual. A better local score is therefore not, by itself, a stronger claim about the deployment. Safeguard research cannot stop at raising local scores; a gain has to be judged by whether it makes a deployed system any safer.

Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questions as to what mechanisms underlie how LLMs perform machine translation between languages. Motivated by recent interpretability findings–namely, that LLMs use massively multilingual latent feature representations to perform language modeling–we propose the interlingua hypothesis. The hypothesis holds that language models translate by reading a source sentence into a latent feature space, and generate a target sentence by reading from the latent feature space. We show three lines of evidence in support of this hypothesis: (1) variance in BLEU across language pairs is largely predictable from language-specific competences with no language pair-specific interaction terms; (2) many model components are causally influential in both monolingual tasks and translation tasks; and (3) fine-tuning on monolingual data recovers a large proportion of translation improvements relative to fine-tuning on aligned documents. Together, these provide convergent evidence in support of the interlingua hypothesis, and suggest new ways of understanding and improving how LLMs can be leveraged to perform translation tasks.

Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop question answering (QA). Graph-based RAG captures multi-step relationships but suffers from severe semantic drift and high online latency due to noisy global graph traversals. Thus, we propose ISO-RAG (ISOperimetric Retrieval-Augmented Generation), a geometry-aware RAG framework. By projecting the underlying knowledge graph into a hyperbolic Poincare ball to precompute node-wise isoperimetric profiles, ISO-RAG prunes spurious edges during retrieval, restricting the search space to a strictly localized subgraph. This topological purification regulates Personalized PageRank (PPR) diffusion driving the retrieval process, ensuring exact and low-latency convergence. Experiments on multi-hop QA benchmarks demonstrate that ISO-RAG outperforms state-of-the-art baselines by average absolute gains of 10.0% in retrieval recall and 4.3% in downstream exact match, achieving a superior accuracy-efficiency trade-off by fundamentally eliminating the latency bottleneck of global traversals. Our source code is available at https://github.com/ZaiizaiZHANG/ISO-RAG.

Artificial intelligence systems increasingly enact market-facing promises through chatbots, recommendation systems, automated decisions, and generative interfaces. Their failures, misuse, and misrepresentation raise a question that conventional brand-crisis models do not fully specify: how do stakeholders assign responsibility when technical causation, customer-facing control, and governance duties are distributed across an AI system, developer, deployer, vendor, and user? This conceptual paper develops a sociotechnical process theory from a structured, federated scoping synthesis of verified academic and primary sources. It distinguishes an AI/algorithmic incident from an AI-related organisational crisis and, in turn, from an AI-related organisational scandal. The framework proposes that incident configuration shapes actor-specific attribution; attribution informs capability, integrity, fairness, and relationship appraisals; and public moralisation may, but need not, escalate an incident into scandal. The theory offers a reconciliation of findings that algorithm involvement can buffer negative brand reactions in some settings while robot and chatbot failures can redirect responsibility to an associated firm in others. It introduces accountable transparency as a proposed response configuration that combines timely notice, an intelligible account, role-responsibility acknowledgement, remedy, evidence of correction, and recourse. The evidence supports conditional, proximal inferences about blame, trust, satisfaction, firm evaluation, and communication credibility more strongly than claims about durable reputation, brand equity, or market performance.

Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes system. It includes 33,686 posts for evaluating evidence-level conflict resolution, and 54,474 instances for evaluating aggregation-level prioritization. Additionally, we propose CoVer, a factual adjudication framework with three-stage pipelines: evidence schema normalization, factual consensus and support verification. This prioritizes evidence over noise to prevent it from compromising the final verdict. Technical evaluations show that CoVer achieves strong performance compared with state-of-the-art baselines across ContraNote (86.0% Acc., 68.0% mac. F1, 64.5 bal. Acc. on Conflict; and 88.5% Acc., 88.5 mac. F1 and 89.2 bal. Acc. on Prioritization), CONFACT-HumC (88.4% Acc.) and CONFACT-ModC (89.4% Acc.).

Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics. Although high-fidelity CFD resolves these mechanisms, its cost limits repeated use in design and control. Standard field-level surrogate training, however, does not distinguish the flow regions that contribute most strongly to the aerodynamic loads. We introduce VATO (Vortex-Force-Aware Transformer Operator), which couples the Vortex Force Map (VFM) method to a geometry-aware neural operator through two complementary mechanisms. VATO-S adds training-only supervision of the local VFM force-contribution field, with no increase in model size or inference cost. VATO-A uses VFM contribution and sensitivity fields to prioritise force-relevant source locations for residual cross attention. The methods are evaluated on unsteady CFD data for double-edged-plate aerofoils over 54 trajectories from nine geometries. Over lead times of 1-20~ms, VATO-S reduces velocity, pressure, and vorticity errors by 10.4%, 1.0%, and 15.6%, respectively, while VATO-A achieves reductions of 15.8%, 7.5%, and 31.2%. VATO-S gives the lowest VFM-derived drag error, whereas VATO-A gives the lowest pressure-derived lift and drag errors. Over lead times extending 50% beyond the training range, VATO-A retains a 26.9% reduction in vorticity error and larger improvements in all four force readouts, despite reduced gains in velocity and pressure. These results show that force-aware operator learning can improve both flow-field prediction and aerodynamic functional accuracy in unsteady separated flows.

Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ read $\rightarrow$ retype loop, creating conversational AI fatigue, cognitive load, and eventual task abandonment. To mitigate this, we present RecalibrateGPT, a system introducing five cross-turn operators (Anchor, Replay, Delta, Scope, and Steer) that each target a distinct fatigue type, recalibrating LLM responses through a structured panel by acting on the full conversation history with a single click. Users invoke these operators through the AssistiveButton in one of three operator palette layouts: Vertical, Arc, or Tablet. We conducted two pilot studies with the same 12 advanced LLM users. An initial formative qualitative study identifies a taxonomy of four fatigue types (retyping, scanning, decision paralysis, and context drift) and derives two design objectives for RecalibrateGPT. A follow-up quantitative evaluation finds it reduces perceived cognitive workload by half (NASA-TLX = 2.7) at high perceived usability (SUS = 86.5), suggesting AI fatigue is not just a model-quality issue but an interaction-flow cost that interfaces can remove.

Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues like order, direction, and motion dynamics. Standard datasets mask this limitation by enabling models to exploit static spatial shortcuts. To systematically evaluate this, we introduce XTE-Bench, a diagnostic probe revealing that even large-scale video-language models struggle with basic temporal reasoning, indicating that parameter scaling alone is insufficient to resolve this flaw. To address this, we propose Cross-Modal Temporal Edits (XTE), a self-supervised framework that injects precise temporal supervision. By performing synchronized video-text transformations, XTE generates hard temporal negatives without manual annotation. We instantiate this with ViTAL-X, a lightweight model that equips frozen image-text backbones with temporal awareness while preserving their foundational spatial knowledge. Across six temporal benchmarks, ViTAL-X achieves state-of-the-art performance. Utilizing only 0.4B parameters and 1M training clips, ViTAL-X outperforms 7B-parameter models and surpasses baselines trained on 600x more data. These results demonstrate that targeted, high-quality temporal alignment provides a highly efficient alternative to pure scaling.

In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming “$\mathsf{ETH}$ for $\mathsf{PPAD}$", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first radically uncoupled algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a layered variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.

Conventional neural networks learn predominantly through affine transformations followed by nonlinear activations, while elapsed time is often treated as an auxiliary feature or assumed to be uniformly sampled. This paper introduces Wave Function Backpropagation (WFB), a wave-parameterized learning formulation in which neural responses are represented by learnable amplitude, wavenumber, angular frequency, and phase. The formulation associates an observed state with its temporal interval Delta t through the phase of a differentiable spatiotemporal wave. We derive standard WFB gradients and a spatial-curvature correction based on the Laplacian of the wave response. WFB is instantiated in a deliberately feed-forward trajectory predictor to provide a controlled proof of concept; sequence learning is outside the scope of the present evaluation. With motion features, STD-WFB using real intervals reduces average displacement error (ADE) by 20.4% relative to the original FFN baseline. In a new position-only evaluation that removes temporal leakage through precomputed velocity and acceleration, real-interval WFB reduces ADE by 10.4% relative to the original FFN and remains competitive with parameter-matched ReLU controls, obtaining 2.1% lower mean ADE than the matched FFN with explicit Delta t. Shuffled-interval WFB attains the lowest mean ADE, indicating that the present evidence supports the effectiveness of the wave representation but does not attribute the gain to interval alignment. These results establish WFB as a viable structured feed-forward learning formulation and define a clear basis for subsequent architectural studies.

Physical fault injection can turn brief hardware disturbances into security failures such as key recovery, authentication bypass, and unintended control flow. Finding effective faults is difficult because many interacting parameters create a large search space, successful settings are sparse and target-dependent, and each hardware attempt provides limited feedback. Under fixed testing time, efficient search is therefore critical for assessing fault sensitivity. We present GlitchLab, an online hardware-in-the-loop platform that treats delay as a timing gate, voltage and pulse duration as severity controls, and hardware outcomes as structured feedback. It implements RL-Q (Q-learning-based reinforcement learning), a structured bandit for discovery, and Structured-Outcome-Based Adaptive Search (SOBAS), a model-based policy for fault reproduction. Both policies find a target fault in every AES, password, and control-flow campaign. On AES and control flow, they require 2-85x fewer attempts and 26-1,237x less time than the baselines; on password, both succeed while the baselines fail within 5,000 attempts. After discovery, SOBAS reproduces faults 7.3-21x more often, while RL-Q identifies 30% more distinct AES settings.

Object scaling serves as a fundamental spatial manipulation that enables complex and productive tasks in XR environments. This paper investigates unimanual scaling techniques for XR using gaze and hand interactions. We propose UniScale, a set of unimanual alternatives to the standard bimanual pinch, allowing users to scale objects while preserving hand availability for concurrent spatial manipulations. We design five distinct mapping strategies based on physical metaphors, exploring unimanual control that varies depth, angle, micro-gestures, and finger-distance input. We then compare these techniques against a standard bimanual baseline, in which users adjust the inter-hand distance via a bimanual pinch gesture. In a user study, we evaluate their effectiveness in a 3D object scaling task under both clutching and clutching-free conditions. The results indicate that while bimanual scaling relies on clutching for stable control, unimanual techniques excel in clutching-free conditions, significantly reducing physical hand movement. From the results, we derive valuable design implications for developing efficient 3D multimodal interactions in XR.

Agentic AI systems are increasingly embedded in scientific workflows, including literature synthesis, hypothesis generation, tool use, writing, and peer review. However, existing surveys and evaluations often emphasize task performance while underexamining how humans and agents coordinate under different epistemic conditions of scientific work. This survey introduces CSCW$\times$Kuhn, a coordination-aware framework that connects computer-supported cooperative work dimensions with distinct scientific contexts. Using this framework, we synthesize recent human–agent systems and benchmarks to examine how coordination demands and failure risks may vary across contexts. Our synthesis identifies five recurring failure modes: procedural drift, grounding substitution, evaluative flattening, proxy optimization, and epistemic black-boxing, and argues for evaluations that move beyond task accuracy and toward grounding, provenance, disagreement preservation, and long-horizon scientific reliability. Our corpus and coding artifact are available at https://github.com/jenlia024/CSCWxKuhn-artifact.

Forecasting local elections is difficult because electoral competition is geographically heterogeneous, highly overdispersed, and characterized by many party-municipality combinations with little or no electoral activity. This article develops a bounded neural zero-inflated negative binomial (ZINB) model for forecasting party-level vote counts in Swedish municipal elections. The model combines a count component for expected votes, a zero-inflation component for structural electoral absence, municipality-specific dispersion, and learned embeddings capturing latent party, municipality, and party-municipality structure. Model training relies on data from the 2014, 2018, and 2022 Swedish municipal elections and performance is evaluated on a held-out set of municipalities. Testing results show strong predictive accuracy in both vote counts and vote shares. Explanatory diagnostics indicate that latent party structure, local party-municipality relationships, electoral persistence, organizational capacity, and candidate-electorate representational similarity are among the most important determinants of predictive performance. Following model evaluation and diagnostics, the selected specification is refit on all historical data and applied to generate forecasts for the 2026 municipal elections. The proposed framework provides a flexible approach for studying local electoral competition in multiparty systems characterized by heterogeneous party presence and substantial geographic variation.

Bare-metal server provisioning systems typically decompress OS images into RAM before writing them to disk. When servers have insufficient RAM to hold the decompressed image (increasingly common as OS images grow due to AI/ML toolkits, GPU drivers, and firmware stacks), provisioning fails entirely. This paper presents a streaming installation technique that combines partial decompression for metadata extraction with pipeline-based disk writing, enabling OS installation on hosts where available RAM is less than the decompressed image size. The method decompresses only the first 30MB of a compressed image to extract the GPT partition table, calculates the target filesystem offset, then streams the full image through a kernel pipe buffer (64KB) directly to disk at the calculated offset, never storing the decompressed data in memory or on disk. Deployed across a production fleet of memory-constrained bare-metal servers, the technique achieves 100% provisioning success where the standard approach fails entirely.

Coding agents are increasingly moving beyond text-based software tasks to reconstruct visual targets through code. This capability, visual coding, requires agents to translate their understanding of visual targets into executable code. Slides provide a natural testbed for this capability, combining rich visual structure with objects that can be programmatically created and edited. To measure this capability, we introduce PPTBench, a benchmark for reconstructing scientific flow diagrams as editable PowerPoint slides. PPTBench covers 500 scientific flow-diagram tasks across 10 presentation domains, drawn from real research papers, and is evaluated with a four-stage agentic judge covering artifact validity, process and connector fidelity, rendering quality, and visual fidelity. Evaluation of ten models across 36 model–harness–effort configurations shows a substantial gap in reliable visual coding: the best configuration achieves 77.34, while the median across configurations is 24.38. Fine-grained analysis shows that agents can generally produce valid slide files, but struggle to produce high-quality reconstructions that faithfully recover the semantics and visual structure of the target. Further analysis shows that increasing reasoning effort primarily improves hard-gate passage rather than mean detail quality on each configuration's passing tasks, while configurations with more inspection tend to achieve higher overall scores. PPTBench establishes a measurable testbed for studying visual coding and advancing agents toward more reliable visual creation.

Automated segmentation of cryo-electron tomograms routinely produces masks that are voxel-accurate but topologically broken: membranes fragment, organelles merge into one another, and enclosed cavities collapse. Existing topology-aware losses reduce these violations but cannot eliminate them, because topology is encouraged through gradient pressure rather than structurally enforced. We introduce TopoFuse, which reframes topology as a differentiable projection operator rather than a loss penalty. At each forward pass, the projection operator $\mathrm{Proj}_T$ (a PH-guided sparse edit) identifies the critical voxels responsible for topological violations via bottleneck matching and applies sparse edits to satisfy a specified topology target (diagram feature counts and lifetime budgets) for dimensions $d \in \{0,2\}$. If the projection converges, the output satisfies those constraints on the downsampled grid ($s=2$); when it does not, a repair certificate exposes this explicitly, enabling downstream filtering. A topology prior head predicts the correction target directly from input features, removing any dependence on ground-truth topology at inference. Across three cryo-ET benchmarks, TopoFuse reduces Betti number error by 54% over the strongest soft-loss baseline ($p < 0.001$), improves Dice by 4.6 points, and edits only 3.1% of voxels to achieve this.

Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input support, or physical parameters change. We asked whether such changes call for a stateful adaptive controller, or whether it is enough to validate the candidate models again on each new batch. To study this question, we built RegimeShift-Surrogates, a reproducible streaming benchmark spanning eight analytic and dynamical tasks, four stationary or shifting regimes, ten held-out seeds, and eight classical, multilayer-perceptron, and Kolmogorov-Arnold network surrogates. The confirmatory run contains 30,720 model fits and 3,200 scored deployment windows. Choosing the model with the lowest validation loss in the current window yields mean log regret 0.091 against a per-window oracle; the best fixed model chosen in hindsight yields 0.192. The paired difference is -0.101 (hierarchical bootstrap 95% CI [-0.165, -0.040]; Holm-adjusted p = 0.0469), with revalidation ahead in 26 of 32 task-scenario combinations. None of the stateful alternatives, including exponential smoothing, dual-timescale adaptation, Page-Hinkley resets, or margin gating, improves the pooled result, and delayed bias correction makes it worse. Oracle choices also differ substantially by task: k-nearest neighbors dominate the damped oscillator, vanilla KAN is often selected for two-dimensional surfaces, and MLPs lead on the Runge and Van der Pol tasks. In this benchmark, fresh validation evidence is useful; carrying old evidence forward is often not.

The complexity of time-domain simulation of modern power systems has increased significantly because converter-based resources introduce control dynamics that must be simulated alongside slower system-level and fast electromagnetic dynamics. The resulting wide range of timescales may force classical time-domain solvers to use small timesteps, complicate the solution of nonlinear equations at each timestep, and reduce solver reliability under strongly nonlinear and multi-timescale transient conditions. This paper introduces RAPTOR, a first-of-its-kind time-domain simulation framework for power system dynamic simulations. At its core, RAPTOR introduces a new integration technique that represents the unknown trajectory of hybrid differential-algebraic equations (DAEs) over a time interval using a physics-informed random-projection neural network (PIRPNN) built from fixed Gaussian radial basis functions (RBFs). A nonlinear solver, e.g., Newton-Raphson, determines how to combine the fixed RBFs so that the resulting trajectory satisfies the governing equations. By combining RBFs with broad and localized shapes, RAPTOR can represent complex multi-timescale behavior over comparatively long time intervals. This enables larger effective simulation advances, fewer overall nonlinear solver iterations, and faster integration over long time horizons. Numerical studies on stiff RMS models, IEEE 9-, 14-, 39-, 57-, and 118-bus RMS simulation benchmarks, and EMT test cases show that RAPTOR accurately finds solutions with substantially fewer sequential simulation advances while offering superior accuracy-runtime performance. With speedups of over 10x in certain cases, these results showcase RAPTOR's potential to outperform long-standing and widely used integration methods, such as the Radau method and the trapezoidal rule.

Verification-aware languages, such as Dafny, integrate logical constructs into code and enable automatic verification of program correctness. However, tests remain helpful in scenarios that verification alone does not address (e.g., to support test-driven development). Existing Dafny test generation tools are implementation-based, limiting their applicability in this context. We present DSpec2Test, a specification-driven test generation tool for Dafny that automatically derives tests from formal specifications, without considering implementation details. Our tool extends Dafny's generate-tests command with a new blackbox mode based on Disjunctive Normal Form (DNF) equivalence class partitioning and optional Boundary Value Analysis (BVA). DSpec2Test relies on the Z3 SMT solver to synthesize inputs and expected outputs that meet the specification-derived constraints. We evaluate DSpec2Test on programs from DafnyBench mutated using MutDafny and compare it against Dafny's existing implementation-driven Block mode. DSpec2Test achieves a 93.9% mutation kill rate on a dataset of 131 mutants, outperforming Block's 82.4%, and uniquely killing 17 mutants. These results suggest that specification-driven testing is an effective and complementary approach for testing Dafny programs.

Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy guarantees characterize randomized mechanisms, whereas operational output control concerns whether a trained model selectively reduces the likelihood of sensitive content in its outputs. In this work, we investigate the latter together with continual-learning utility under realistic task evolution. Retention and privacy correction operate at different granularities: task acquisition requires broad preservation of current- and old-task behavior, whereas privacy correction targets sparse annotated positions. Joint optimization leaves the current-task preservation target continually changing. We propose SPARK, a retention-correction decomposition that first freezes the learned post-task distribution and then applies selective correction around this stable reference. Self-Distillation Replay learns the current task while distilling behavior from previous tasks, and Post-Task Privacy Correction reduces annotated-PII likelihood while anchoring current- and old-task non-PII behavior to the resulting checkpoint. Extensive evaluations demonstrate that SPARK achieves effective selective PII suppression while preserving strong continual-learning utility and knowledge retention across diverse settings. Code and data will be released upon publication.

Evaluations that use a large language model (LLM) as a judge have begun to borrow reliability statistics from classical test theory and its extensions. We examine three such statistics that need one administration and no gold labels. None of them can isolate the judge, because one judge under one prompt supplies no variance component of its own. Claude Haiku 4.5 judged 210 constructed short answers against ten-element checklists. On the 180 with parsed verdicts, the Kuder-Richardson coefficient (KR-20) came out at 0.5223 on the judge's verdicts and 0.5231 on error-free gold verdicts. In simulation, bank design alone moves KR-20 from 0.01 to 0.68 at the judge's measured 4.72% error rate. The dependability index $\Phi(\lambda)$, a ratio of mean squared distances from the pass mark, sits 0.22 to 0.38 below the judge's accuracy against gold and returns 0.54 to 0.68 on error-free gold verdicts. Livingston-Lewis accuracy treats the rubric elements as a sample, and at a pass mark of five elements it credits error-free gold scores with 0.78, close to the judge's 0.81. A statement about the judge therefore needs gold labels or a varied scorer facet, and a reliability ratio needs the bank's spread beside it. One of the four closest judge-evaluation papers varies the prompt and still reads a reliability below 0.7 as a sign that a model cannot serve as a judge, although that reliability moves with the spread of the samples scored. We derive a decision table and four reporting lines from these two rules.

LLM agents that iteratively reason, plan, and invoke tools create workload profiles fundamentally different from single-pass inference, yet how their energy consumption is distributed across hardware components and workload phases remains poorly understood. Characterizing these workloads therefore requires simultaneous visibility into both component-level power and phase-level execution. We conduct a full-stack energy profiling study combining NVML GPU counters, Intel RAPL CPU/DRAM counters, and Intelligent Platform Management Interface (IPMI) system-level sensors on 2x NVIDIA RTX PRO 6000 Blackwell GPUs, and profile three representative workloads with Qwen3.8-27B. For mathematical reasoning, we compare thinking-enabled and thinking-disabled modes. Our measurements reveal that GPU-only telemetry misses 41-45% of system energy across all three workloads, with non-GPU components accounting for the remainder. In our setup, the sequential agent workload consumes 63x more system energy per output token than saturated serving, reflecting the absence of batching, context growth across turns, and tool-induced idle periods. Extended thinking generates 21-75% more tokens per problem, while per-token energy differs by less than 1% between modes within each dataset, indicating that the resulting increase in energy is driven by output volume rather than a change in per-token efficiency. Continuous batching improves system-level energy efficiency by 3.2x from 1 to 16 requests per second, as GPU power plateaus while throughput continues to increase with batching depth. For the memory-bandwidth-bound reasoning workload, throughput remains unchanged under per-GPU power caps of 400-600 W but drops sharply at 300 W. These findings suggest that context-management techniques such as summarization and selective retrieval may help reduce energy consumption in agent deployments.

Accurate pedestrian trajectory prediction is important for proactive road-safety applications, particularly at urban intersections where pedestrian motion is shaped by both vehicle interactions and crossing context. This study presents a safety-oriented trajectory-prediction framework that combines pedestrian motion history with Time-to-Collision (TTC) information and crossing-zone indicators. Using naturalistic trajectories from one urban intersection in the inD (Intersection Drone) dataset, several neural architectures were evaluated with 1.6 s observation and 2.4 s prediction horizons. A pooled Long Short-Term Memory (LSTM) separately encodes TTC histories and crossing-zone context before integrating them with pedestrian positions. In addition to conventional Average Displacement Error (ADE) and Final Displacement Error (FDE), prediction performance was assessed using the frequency and magnitude of errors exceeding a study-defined 1 m tolerance. A weighted loss was also introduced to place greater training emphasis on large coordinate-wise errors. Applying this loss to the position-only LSTM reduced ADE from 0.210 to 0.190 m and FDE from 0.550 to 0.503 m, while reducing ADE and FDE exceedance counts by 34.8% and 19.8%, respectively. The final pooled configuration incorporating TTC and crossing-zone information achieved an ADE of 0.184 m and FDE of 0.491 m, with further reductions of 33.5% and 6.3% in ADE and FDE exceedance counts relative to the safety-oriented position-only LSTM. The results indicate that safety-oriented training and structured integration of interaction and contextual information can reduce large trajectory-prediction errors, although broader validation across pedestrians, sites, and datasets is required.

As quantum computing evolves, the demand for high-quality quantum software is increasing. Classical software quality models, such as McCall's model, provide a useful foundation, but they do not explicitly capture distinctive properties of quantum software, including probabilistic measurement outcomes, backend-dependent behavior, and hybrid quantum-classical workflows. This paper proposes a base quality model for quantum software using McCall's factor-criterion-metric structure as the organizing backbone. It broadens the set of quality factors by drawing on representative classical software quality models and standards and introduces quantum-specific extensions only where needed. We define the resulting factor set and quality criteria, provide a many-to-many mapping of core factor-to-criterion relationships, discuss representative candidate metrics together with the execution, reference, and interpretation conditions needed to use them, and illustrate how the resulting model can be applied across the quantum software lifecycle. The model is intended as a common starting point for structuring, assessing, and communicating quality concerns in quantum software while supporting context-specific adaptation. Further expert feedback, case studies, and empirical studies can be used to evaluate and refine the model and its application across different quantum software contexts.

Industrial Control Systems (ICS) are increasingly exposed to cyber-physical attacks that manifest as subtle and temporally evolving deviations in process behavior. Detecting such anomalies requires reasoning over persistence, cross-signal dependencies, and process-level constraints. Digital Twins (DTs) encode system knowledge through physical and logical relationships between signals, but existing DT-based approaches rely on instantaneous rule violations and lack mechanisms to aggregate weak evidence over time. This paper proposes a training-free anomaly detection method that combines deterministic DT constraints with explicit temporal memory. The DT monitors process signals and produces anomaly scores based on constraint violations, while a lightweight memory mechanism captures persistence and contextual relationships across time. The approach is evaluated on the HAI and BATADAL datasets. Ablation results show that the memory-less detector fails completely, demonstrating that temporal aggregation is essential for DT-based detection. On HAI, the memory-aware DT achieves stable detection with only 4 false alarm events, and on BATADAL, it remains effective without retraining, with 21 false alarms under domain shift. In comparison, Isolation Forest (IF) produces substantially more false alarms (328 on HAI and 127 on BATADAL), while Autoencoder (AE) exhibits dataset-dependent behavior, achieving high precision on BATADAL but low recall and inconsistent performance overall. A gated LLM is used for post-hoc interpretation, providing structured explanations without affecting detection performance. Our findings highlight the importance of temporal memory in constraint-based detection and support the use of decoupled reasoning for interpretability in ICS monitoring.

Research data infrastructure measures metadata completeness, the share of fields populated. This is the wrong quantity: a populated field is not a joinable field. We measure comparability instead: whether two records can be used together, and for what. Working from 180,877 records across eight public sources, we adapt measurement invariance from psychometrics into a four-rung ladder, each rung established by its own test and licensing one specific comparison. Over all 167,331 pairs of gas chromatography analyses in a public metabolomics repository, 100% reach the bottom rung, 58.85% the second, 0.072% the third, and exactly two pairs reach the rung that licenses comparing values directly, an upper bound under a generous test. The deficit is recoverable: the missing values survive in prose. We formalise crosswalking as five operations ordered by reliability, each with a characteristic failure mode. The temperature programme that determines retention is structured in none of a second repository's 355 gas chromatography studies yet written in prose in 78.6%; we recover 206 ordered programmes comprising 529 steps, audited over three rounds. The perceptual record fails differently: its datasets do not share a language. Among eight that declare they measure odour character in humans, 42.9% of pairs share no descriptor, and two studies rating the same molecules with the same word agree at mean correlation 0.31. Joining volatility measurement to human percept across the entire public record yields 132 molecules. Across seismology, meteorology, metrology and chemistry, a field is populated when the primary consumer cannot complete the primary task without it: the same optional, unvalidated field sits at 100% in one discipline and near zero in another. Resources should publish a conformance ledger, reporting what is missing as a tracked quantity; we release one, with 48,356 triples.