Papers

The performance of textual neural models often degrades when their inputs are corrupted by noise such as typos, OCR errors, or dropped words. We study the degradation rate across neural models, both sentence embeddings and decoder-only LLMs, and find that how consistent it is depends on the scale of the noise: under word-level noise, models with very different architectures decline along nearly the same curve, while under character-level noise they separate. We further identify the determining factor to be the training objective, not the architecture: eight encoders spanning six pretraining paradigms are scattered initially, and collapse onto a common curve after a short contrastive training recipe. We trace the word/character split to tokenization: a single character edit forces the tokenizer to re-segment the surrounding word, disturbing the token sequence far more than dropping a whole word does. This finding and its underlying mechanism provide a practical means to predict a model's robustness to noise without any noisy evaluation, and to install robustness at a chosen noise scale through noise-augmented training.

Frontier language models are increasingly marketed as omni systems that can perceive and respond across modalities. Existing evaluation frameworks, however, focus almost exclusively on bimodal understanding, typically text plus one other modality. We propose the Modality Maturity Index (MMI), a benchmark designed to evaluate the multimodal capabilities of large language models across five modalities (text, image, audio, video and document) and combinations of up to three modalities in both inputs and outputs. MMI consists of 893 questions, each carefully crafted to require the model to demonstrate its understanding of multiple input modalities and to generate responses that incorporate various output formats. The questions are designed to be self-contained, with clear expectations for the correct modality or mix of modalities required for an accurate response. Every MMI prompt carries human-authored rubric criteria for each output modality expected in the response; a model's MMI Value expresses the average of the per-modality scores for each prompt. Because low scores can reflect either failure to generate a modality (lack of presence) or failure to generate correct content, we introduce also a supplementary Modality Presence Score (MPS), a per-prompt F1 over the expected output modalities. Applying MMI to five frontier multimodal models, we find that the MPS ranges from only 15.6 (Claude Opus 4.6) to 34.9 (GPT-5.4). Given the low availability of returned modalities to even grade, we report MPS as our main result pending model improvements. To assess the viability of judging output correctness with LLM judges and rubrics, we run a separate experiment with custom generation tools. On the assets that generates, we find that an LLM judge applying the rubrics agrees with rubric-blind human annotators (who score the outputs directly and never see the criteria) on 70.8% of judgments.

AI-assisted development tools enable software engineers to generate implementations at substantially higher speed and volume than in traditional workflows. Software teams have long relied on guardrails – standing control mechanisms such as code review, linting, testing, and CI/CD pipelines – to maintain quality and coordination. High-throughput AI-assisted generation increases pressure on these guardrails – straining their capacity to keep pace with the volume and rate of generated changes – and reshapes how organizations supervise development workflows, yet relatively little is known about how existing guardrails evolve in response. We conducted a qualitative interview study with five software engineering practitioners, situated within a broader practitioner survey. Our findings indicate that organizations distribute the work of supervision across multiple guardrail layers: preventive guardrails (produced by externalizing architectural intent and conventions into machine-interpretable form), executable guardrails (linting, testing, and CI/CD repurposed as scalable supervision infrastructure), and human oversight (shifting from line-by-line inspection toward supervisory interpretation focused on architectural reasoning, explainability, and long-term maintainability). We characterize this as a transition from review- centric guardrails toward layered supervision, in which no single guardrail carries the supervision load alone.

Steering-based planners require solutions to state-to-state boundary value problems, which can be inaccessible for nonlinear platforms. Forward propagation evades the steering requirement, but the finite-sample behavior of the associated planners remains uncharacterized and their implementations underperform in practice. This paper develops a propagation-based kinodynamic planner with deterministic finite-sample near-optimality guarantees. We work within the large class of differentially flat nonlinear systems and show that a forward tree of locally dispersive control commands contains a near-optimal trajectory at a certified tree size. We provide a general mechanism to construct dispersive command sets for control-affine systems, which are necessary to implement the search algorithm prescribed by the theory. We show that covering the certified trajectory class irrespective of cost provably demands a tree exponentially sized in the problem horizon, and present a cost-conditioned dominance pruning procedure that retains near-optimality at a tree size polynomial in the horizon. We implement the resulting search algorithm, Dispersive Forward Tree search (DFT*), as breadth-first expansion of the forward tree, which maps naturally onto parallel hardware. We design efficient dispersive samplers for the unicycle, the trailer car, and the quadrotor and evaluate challenging planning tasks for these platforms. DFT* delivers consistently competitive and often substantially better solution quality than state-of-the-art kinodynamic planners at comparable solution times on embedded-tier processors, accelerating further as parallel compute is scaled. We also implement DFT* in a receding-horizon loop to demonstrate real-time planning in dynamic environments at embedded-tier compute budgets.

Large language models can now generate complex, multi-step mathematical proofs, but reliably determining their correctness and localizing early logical errors remains a critical challenge. Existing evaluation approaches largely depend on model-based natural-language judgments, which often overlook local reasoning gaps. While formal theorem provers like Lean offer a path to rigorous verification, using them to evaluate informal text requires solving locality and semantic mismatches: a prover might bypass a local flaw by proving an overly broad target, or validate an auto-formalized statement that drifts from the original mathematical intent. To address this, we introduce FaithSieve, a Lean-assisted framework for fine-grained evaluation of natural-language mathematical proofs. FaithSieve decomposes coarse proof steps into local reasoning units, extracts typed proof obligations, and verifies them through a formal evaluation agent. Formal validation is gated by semantic alignment scoring, so Lean evidence is incorporated only when the formal statement faithfully preserves the context, objects, and logical form of the original claim. We construct two expert-verified datasets, ProofLoc-Olympiad and ProofLoc-University, to benchmark first-error localization. On the 350-problem Olympiad dataset, FaithSieve using a GPT-5.4 backbone achieves 81.43% exact first-error accuracy, outperforming the direct-judging baseline of 72.29%. Furthermore, on the 200-problem ProofLoc-University benchmark spanning six advanced domains, FaithSieve reaches 84.5% exact accuracy, compared to 75.0% for the direct judge. Our work demonstrates that decomposing proofs into fine-grained units and grounding them with faithful formal evidence significantly improves reliable evaluation of natural-language reasoning.

Modern machine learning models rely on large amounts of labeled data. However, manual annotation of large-scale datasets is expensive and time-consuming. Label spreading is a semi-supervised learning technique that addresses this challenge by propagating information from a few labeled examples to a larger pool of unlabeled data. Despite its effectiveness, its application to large-scale, high-dimensional datasets is limited by computational costs and memory constraints. To address these limitations, we propose Algebraic Multigrid Acceleration for Efficient Label Spreading (AMELS), an efficient label spreading framework that improves scalability by fast construction of neighborhood graphs and the incorporation of algebraic multigrid solvers. The latter is an iterative solver that replaces the ordinary random walk iteration typically performed in label spreading. Due to the multilevel nature of algebraic multigrid solvers, AMELS spreads given label information across a graph of any size in a single multigrid cycle. We demonstrate that AMELS achieves significant runtime reductions compared to existing implementations while also being more robust to hyperparameter choices in terms of both runtime and classification accuracy. Our framework therefore enables efficient label spreading on large-scale image datasets and produces accurate labels even when only a few labeled samples are available.

A large language model (LLM) guardrail for a self-adaptive system (SAS) may issue an approval that is correct at check time but stale by actuation. This creates an Execute-stage time-of-check to time-of-use (TOCTOU) hazard. We study verdict freshness: whether a guardrail verdict remains valid when used. We distinguish three quantities that answer different questions: all-candidate verdict change under fixed-action replay, oracle-labeled approval expiry on recorded closed-loop trajectories, and judge-conditioned use-time invalidity. Across five reproducible SAS environments, all-candidate verdict-change rates span 5.3-48.4% at a common replay shift of eight simulator steps. We introduce the Freshness-Bounded Shield (FBS), which estimates each approval's validity horizon from its safe-side margin and recent feature volatility, without an explicit plant-dynamics model. Using fixed settings documented in the artifact, FBS reduces oracle-labeled approval-expiry rates from 3.4-24.7% to 0-1.8% at the same shift. A separate audit of four LLM judges finds nonzero judge-conditioned use-time invalidity in every approval stream. We formulate a freshness contract: every approval must be correct at check time and remain valid at use time.

Physics-Informed Neural Networks (PINNs) have recently gained considerable attention as a mesh-free framework for solving partial differential equations. Nevertheless, their performance deteriorates when applied to strongly coupled multiphysics systems, such as Biot's consolidation model, due to severely ill-conditioned optimization landscapes. In this work, we propose a robust PINN-based solver, termed FS-ENGD-PINN, which synergistically integrates physics-based decoupling with geometry-aware optimization. Specifically, the Fixed-Stress (FS) splitting scheme is employed to decompose the coupled poroelastic system into contractive mechanics and flow subproblems, thereby significantly improving training stability and convergence. To further accelerate optimization, we adopt Energy Natural Gradient Descent (ENGD), which approximates the Newton direction in function space effectively mitigates stiffness-induced slow convergence. Moreover, to address volumetric locking arising in the nearly incompressible regime, we incorporate a three-field mixed formulation with an additional total pressure variable into the PINN framework. Extensive numerical experiments demonstrate that the proposed FS-ENGD-PINN consistently outperforms standard PINN formulations in terms of accuracy and robustness, providing a unified and reliable learning-based solver for poroelasticity across a wide range of material parameters.

Urban food environments may reflect broader socioeconomic inequalities, but district-level evidence remains limited in Brazilian cities. This study examined whether indicators of food retail and street-market availability discriminate between levels of social vulnerability across the 96 districts of São Paulo. We conducted an exploratory cross-sectional ecological analysis integrating the São Paulo Social Vulnerability Index (IPVS), establishment records from the Relação Anual de Informações Sociais (RAIS), and street-market data from CAISAN. Census-sector information was aggregated at the district level. Twenty districts without an IPVS classification were excluded, resulting in 76 observations. The outcome distinguished districts classified as IPVS level 1 from those classified as levels 2–7. Predictors described the densities of healthy and unhealthy food establishments, the number of street markets, and the availability of establishments selling fresh or in natura food. Eight conventional machine-learning classifiers were evaluated using leave-one-out cross-validation. Reported mean F-scores ranged from 0.62 to 0.75, with XGBoost obtaining the highest value. In the Random Forest model, the densities of healthy and unhealthy food establishments jointly accounted for approximately 60% of the total impurity-based feature importance. These findings indicate that publicly available food-environment indicators contain information associated with the district-level distribution of social vulnerability. However, the small ecological sample, class imbalance, outcome binarization, and cross-sectional design limit predictive generalization and preclude causal or household-level interpretations.

We study a thermodynamically consistent non-isothermal phase-field system coupling two order parameters and the inverse temperature through a fully non-diagonal Onsager mobility. The model describes the interaction of mass diffusion, heat conduction, and local phase relaxation while conserving mass and internal energy and producing entropy. Global generalised dissipative weak solutions are constructed using a fully discrete approximation. The discrete scheme conserves mass and internal energy and satisfies a discrete entropy inequality. An availability estimate, together with a dimension-adapted barrier, yields strict positivity at fixed mesh and uniform estimates. Compactness then allow passage to the continuous system. Concentration of the singular part of the internal energy is represented by a non-negative defect measure. The entropy-availability structure yields finite dissipation on the infinite time interval and the existence of stationary $\omega$-limit states. Finally, a relative-entropy argument establishes weak-strong uniqueness whenever the weak and strong solutions remain in a bounded thermodynamic state range.

Tool-augmented LLMs must arbitrate between two fallible sources when a tool return conflicts with their parametric memory, yet existing evaluations measure source preference without establishing source correctness. We introduce MemToC, a controlled benchmark for post-tool-return arbitration with executable tools. MemToC comprises 6,504 evaluation episodes constructed from 542 quality-controlled factual questions, independently elicited model-specific closed-book answers, and controlled tool returns of known correctness. These components instantiate four source-correctness cases; tool-error and no-tool conditions are separate controls. Across five open-weight 7-9B models, tool returns strongly dominate elicited closed-book answers. The four instruction-tuned models retain a verified-correct answer against an incorrect tool in only 6.5-17.1% of eligible cases, follow a correct tool in 86.0-93.1%, and repeat the tool return in 78.4-86.0% of cases where both sources are wrong. No cross-model ordering remains stable across three instruction-wording variants with the question and episode content held fixed. We compare prompting with SFT and DPO using chain-level cross-fitting over ToolHop, so questions sharing an underlying fact never straddle training and evaluation. We apply an asymmetric success criterion: correct-answer retention must improve without a detected reduction in correct-tool following. SFT and DPO meet this criterion on the same two of four instruction-tuned backbones. Improvements rarely come cleanly: 19 of 20 tested method-model combinations reduce abstention after tool errors or on unanswerable inputs. Transfer beyond MemToC is positive but partial and depends on the model and presentation frame. Correctness-conditioned arbitration can be improved through fine-tuning, but gains must be evaluated jointly with correct tool use, abstention, and robustness to formulation.

Every memory-based knowledge editor in the SERAC lineage depends on a scope decision: given a query, does a stored edit apply? We report that current knowledge-editing benchmarks cannot measure this decision at all. Using INLAY, a gradient-free editor we built to obtain exact per-query ground truth (the model is frozen, edits live in an external addressable memory, and applying an edit is a bias added along one token's unembedding direction at decode time), we execute every candidate router action on 1,689 queries spanning three datasets and three input conditions. An oracle router choosing the best action every time ties a one-line static policy to four decimal places in all nine dataset-by-condition cells: the maximum attainable gain of any per-query routing method is 0.00 points. Abstention is the sole winning action zero times out of 1,689. The cause is structural: these are counterfactual benchmarks whose evaluation question asks for the post-edit answer, so answering from parametric knowledge is wrong by construction, and a benchmark without negatives cannot reward a classifier's ability to reject. This generalizes beyond our system to the whole scope-classifier family the benchmarks are used to evaluate. We confirm the mechanism directly: constructing the missing condition ourselves, by withholding a query's own edit from the index for half the sample, moves pooled headroom from exactly +0.0000 to +0.0420 and gives abstention its first wins. We also report where INLAY itself does not win (WISE beats it on Qwen2.5-7B CounterFact, and retrieval-augmented generation beats every method we tested, INLAY included, on rigorously matched RippleEdits), and disclose two bugs found during a self-audit of our own routing machinery, neither of which changed a published headline number outside noise.

Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social interactions. Large language models (LLMs) demonstrate behaviour consistent with humans on theory-of-mind tasks, yet whether these models can guide adaptive behaviour through mentalization is unknown. Here we use two economic games with cognitive computational modeling to uncover the latent strategies underlying mentalization in LLMs. We tested individual LLM agents across four model families, DeepSeek, GPT-4.1, GPT-5 and Gemini 2.0 Flash (N = 2,099), against opponents of varying sophistication and examined whether a prompting strategy designed to elicit strategic reasoning improved performance. We benchmarked results against human participants (N = 251) as a comparative measure. Across both games, LLMs showed clear behavioural and computational signatures of mentalizing that differed markedly by model provider and size. Strategic prompting generally improved performance by inducing more sophisticated reasoning, yet the extent of the benefit differed across the two tasks. Last, GPT-5 agents flexibly adapted their recursive depth of reasoning to increasingly sophisticated opponents, demonstrating superior performance to human participants. Collectively, we demonstrate different capacities for mentalization across LLMs, and highlight cognitive computational modeling as a formal method for assessing comparative intelligence across humans and machines.

Muon has emerged as a strong optimizer for the matrix-valued parameters in large language model pretraining, approximately orthogonalizing its momentum with a few Newton-Schulz iterations. Existing theory either replaces this iteration with the exact polar factor it approximates, or treats its finite depth as an approximation error, and thus the iteration Muon actually runs can only hurt the guarantees. We show that finite Newton-Schulz can instead be beneficial for nonsmooth nonconvex optimization. To this end, we analyze Muon through the online-to-nonconvex conversion, which views the update rule as an online learner and converts its regret bound into a stationarity guarantee. The finite Newton-Schulz iteration smooths the discontinuous polar map into a Lipschitz map of the singular values, and Muon with finite Newton-Schulz can be regarded as an online learner with a smoothed spectral potential. This smoothing is exactly what the conversion needs: we prove that a Newton-Schulz depth growing only logarithmically in the target accuracy suffices for convergence to stationary points in nonsmooth nonconvex optimization, whereas Muon with the exact-polar update may fail to converge. The resulting sample complexity bounds match the best-known guarantees for nonsmooth nonconvex optimization and are optimal for smooth nonconvex optimization up to problem-dependent factors. The argument extends beyond Newton-Schulz to general spectral maps with the same smoothing property.

This paper deals with the computation of the sum of alternating series, whose general terms can be expressed by means of analytic functions. After rewriting the series as a weighted integral with the Abel weight, we employ the sinc (trapezoidal) rule and analyze the remainder term with respect to the number of quadrature points. We provide some numerical experiments to show the reliability of the derived error estimate and to test the algorithm for automatic summation with prescribed accuracy. All the Matlab codes used in the present paper can be found as open-source software at the authors' homepage.

Extracting a shared set of unknown, not directly measurable quantities from multiple, heterogeneous datasets is a common challenge across scientific domains. A prominent example is the combination of datasets obtained from different measurements with different settings (e.g. varying detector resolutions). Analyzing such datasets jointly, rather than independently or after naive merging, is essential for obtaining precise and unbiased estimates of the unknowns, but requires careful treatment of dataset heterogeneity and is computationally demanding. We present a generalized framework for simultaneously analyzing multiple heterogeneous datasets in the context of generative AI-based inverse problem solvers. Building on our recent Scalable Asynchronous Generative Inverse Problem Solver (SAGIPS) framework, we extend the well-established distributed data-parallel training paradigm to non-identically distributed datasets, where each dataset is controlled by the same set of unknown inference parameters but covers a different region of the available feature space. Each dataset is processed through its own forward operator and discriminator, providing complementary constraints that collectively guide a shared generator toward global parameter consistency. We validate the approach using a controlled setup inspired by a multi-detector scattering experiment. We provide numerical evidence that our framework is robust to different data fidelities, which arise from unknown detector systematics in the Rutherford experiment, and we show the scaling behavior on multi-GPU leadership computing systems. The results show that our approach is well suited for real-world multi-dataset analyses in which experimental conditions vary across measurements.

We provide an overview of the problem of jointly testing two hypotheses and estimating a parameter of the selected model. Such problems arise in a variety of applications. First, we present a conceptual introduction to suboptimal and optimal procedures for joint detection and estimation. A numerical example illustrates the advantages of the optimal procedure over suboptimal ones. Next, we discuss how more advanced problem formulations affect the presented results. The second part covers joint detection and estimation in a sequential framework. First, we provide an introduction to sequential analysis through sequential hypothesis testing. Then, suboptimal and optimal sequential procedures for joint detection and estimation are discussed. A numerical example shows the advantages of optimal sequential procedures over suboptimal and optimal sequential procedures with a fixed number of samples. The third part discusses open problems and future research directions in joint detection and estimation.

Static shape estimation of co-manipulative continuum robots (CCRs) is challenging because the continuum arms and manipulated flexible object form a closed chain that must satisfy both static equilibrium and geometric loop-closure constraints. This paper presents a constraint-aware physics-informed neural network (PINN) for static shape estimation of a tendon-driven CCR modeled using the geometric variable strain formulation. The proposed method incorporates a projected static equilibrium residual and a configuration-level geometric residual to enforce the governing mechanics and closed-chain geometry. In simulation, the PINN is compared with a purely data-driven artificial neural network (ANN) under limited and noisy training data. With 140 samples and 50% label noise, the PINN reduces the relative configuration error, equilibrium residual, and closed-chain residual by 67.88%, 67.35%, and 88.06%, respectively. Using the full dataset, the PINN achieves 0.1597% relative configuration error with an inference time of 0.1773 ms, compared with 17.97 s for an iterative nonlinear solver. Experimental fine-tuning reduces the marker RMSE from 2.657 mm to 0.497 mm and increases R2 from -0.788 to 0.937. These results demonstrate accurate, physically consistent, and computationally efficient static shape estimation of closed-chain CCRs.

The threshold theorem states that quantum computations can be made reliable below a physical error threshold, at the cost of additional physical qubits and circuit depth. Recent work has reduced these space and time overheads to polylogarithmic or nearly logarithmic scalings, but whether the cumulative spacetime overhead can be constant has remained unclear. Here, we show that even for the simplest task of preserving quantum information in a quantum memory, under an optimistic noise model and allowing general adaptive protocols, there is an unavoidable logarithmic contribution to the cumulative spacetime overhead. This additional cost can nevertheless be shared among many logical qubits, so sufficiently wide computations, including standard implementations of Shor's algorithm, may still achieve constant relative overhead. We further give a positive-rate CSS code construction that attains the memory bound, identify sufficient conditions under which the same scaling extends from quantum memory to fault-tolerant circuit implementations, and derive circuit-size bounds for subsystem spacetime codes. Our work establishes fundamental limits on the resources required for quantum fault tolerance.

Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning traces to an ever-growing conversation history, causing latency degradation and context-poisoning failures over long horizons. We present SKILL. state, a runtime architecture that replaces append-only conversational history with an explicit, mutable execution state. At each execution step, the model receives only the immutable skill specification, the current structured execution state, and the latest observation. Intermediate reasoning is discarded immediately after producing a validated state update, preventing prompt growth with execution history. Across diverse datasets, models, and execution environments, SKILL. state improves task accuracy while substantially reducing cumulative token consumption. Our results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills.

In this paper, we investigate the low-depth circuit complexity of Group Isomorphism in the multiplication (Cayley) table model. We prove the first circuit lower bounds for Group Isomorphism: namely, we show that every family of depth-$2$ Boolean circuits deciding Group Isomorphism requires quasipolynomial-size. (We also extend this to a limited class of depth-3 circuits, namely $\textsf{CNF}$-of-$\textsf{XOR}$s.) We complement this with upper bounds of uniform depth-$2\frac{1}{2}$ circuits of quasipolynomial-size: depth 3 circuits with poly-logarithmic bottom fan-in. A sequence of previous results from 1970-2025 progressively reduced the circuit depth from polynomial to $3\frac{1}{2}$; all of these results relied on the generator-enumerator strategy and, in fact, applied more generally to quasigroups. In contrast, our depth-$2\frac{1}{2}$ construction follows a fundamentally different strategy that exploits structure more specific to groups. We guess a composition series for each group, together with generators for its terms and the isomorphism types of its composition factors. We then inductively verify that the corresponding extensions at each level of the two composition series are compatible. A central part in this approach brings to bear the extensive work on the Short Presentation Conjecture, in tandem with the algorithmic theory of group extensions and cohomology.

Generative world models provide robots with predictive models of how the world evolves under interaction, with growing potential for simulation, planning, policy evaluation, and robot learning. Beyond clip-level future prediction, a unified generative formulation should relate actions to consequences, support flexible horizons and continuous interaction, and enable reward-driven optimization. We introduce WALL-SS, a world model that generates visual futures through Scale-wise autoregressive Scaling, enabling action-controllable and long-horizon robotic simulation. WALL-SS represents embodied trajectories as causal sequences of temporally interleaved observations and actions, making action-dependent state transitions explicit while naturally supporting variable-length generation, streaming extension through reusable causal states, and direct optimization through sequence probabilities. To make this formulation effective over long horizons, we generate each future observation in a coarse-to-fine manner and develop three complementary components within the same hierarchy. Action-conditioned next-scale prediction injects scale-aligned action representations to improve action-future coupling and model both successful and failed behaviors. Scale-compressed long-horizon memory retains recent interactions at fine resolution while compressing distant observations and actions, with scale-wise dream forcing enhancing robustness to self-generated context. Finally, on-policy alignment optimizes autoregressive visual dynamics with action-following and long-term consistency rewards while preserving the pretrained visual distribution. Experiments show that WALL-SS improves action following and trajectory accuracy, supports coherent minute-long streaming rollout under bounded memory, and consistently benefits from on-policy alignment in reducing action drift and long-horizon inconsistency.

Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a user could edit. To address this, we explore the paradigm of 3D shape as code, leveraging and scaling the coding ability of an LLM for 3D modeling. We introduce Procedura, a novel 3D modeling agent framework that writes an object as a procedural assembly, a parametric program whose named parts are joined by typed, machine-checkable mates. From a text prompt, the agent plans the object as an assembly graph and writes the program part by part, solving each placement from the mated frames rather than guessing it, and admitting a part only once compile, mate, and connectivity checks pass. A decoupled vision critic then refines the assembly one diagnosed fix at a time. Moreover, the same graph carries per-part materials and a simulator-validated articulation. We evaluate on P3D-Bench under its assembly judge, and with the same judge on MechBench-36, our hard-surface benchmark. On both, Procedura outperforms state-of-the-art native 3D generators and every prior 3D-code agent on judged quality, produces the sharpest edges of any method we evaluate, and is the only one whose output is an editable, part-structured program.

Capture-the-Flag (CTF) benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or aggregate scores, overlooking the agent's trajectory to the flag. Consequently actual exploitation is conflated with direct flag exposure, memorized recall, external lookup, guessing, and unsupported claims, potentially overstating the agent's cybersecurity capability. We introduce CTF-ABACUS, a trace-based agent auditing framework that reconstructs each run as an evidence-grounded solve profile. By decomposing agent actions into penetration-testing phases and categorical techniques, it identifies where exploitation occurs, where the flag first appears, and whether the recovered flag is supported by demonstrated behavior. Aggregating solve profiles across agents yields challenge signatures that reveal whether success was achieved via the intended exploit or via shortcut pathways. We apply CTF-ABACUS to 1,435 CTF attempts by six frontier and open-source models on 240 challenges, yielding 2,870 solve profiles under two judge lenses. Trace-verified exploits account for only 62-87% of recovered flags across benchmarks, while shortcut recoveries follow substantially shallower trajectories. These findings shift CTF evaluation from counting recovered flags to verifying demonstrated exploitation and provide a basis for designing benchmarks that better isolate the offensive capabilities.

We present a six-stage framework for auditing the reproducibility of scientific claims across a research literature within the computer science domain, and instantiate our framework for the neuro-symbolic AI (NSAI) subdomain. Instantiating the framework on the NSAI subdomain produced a multi-year audit. Stage one retrieved 5,497 records and removed 3,018 duplicates. Stage two screened the 2,479 unique records at title and abstract, identifying 1,365 self-identified NSAI records, then removed a further 61 at full text for off-topic, non-research, no-quantitative-evaluation, or inaccessible-full-text reasons. Stage three sought a verifiable public code artifact for each of the 1,304 eligible records and found none for 849, leaving 455 to enter the artifact inventory and bounded rerun of stages four and five. We fully or partially reproduced 85 studies, 6.52% of the eligible corpus and 18.68% of attempted reruns. We found that 321 attempted reruns were blocked by missing non- code artifacts and 42 by missing or unusable code repositories. These figures quantify a persistent reproducibility deficit that survives even nominal "code available" declarations, and signal the need for enforced, versioned, and permanently archived artifact bundles in future NSAI publications. We argue that empirical NSAI papers should be required at submission time to provide complete, versioned, and permanently archived artifact bundles.

Accuracy-only benchmarking of reasoning-capable large language models misses a central deployment question: when do extended thinking tokens earn their cost? We introduce the Token Economy Score (TES), a marginal benchmarking metric that measures the accuracy gain of a reasoning model over a non-reasoning baseline, normalized by the generated-token multiplier. We define paired and approximated TES variants for model families with reasoning toggles and frontier models without direct non-reasoning counterparts. We then conduct an empirical benchmarking analysis across 151 model-benchmark evaluation runs on seven benchmarks spanning mathematics, code generation, science reasoning, instruction following, expert knowledge, knowledge recall, and research-level physics. The analysis examines three deployment-facing dimensions: which task structures yield positive marginal reasoning efficiency, how increasing reasoning effort changes TES within model families, and how deployment context changes economic viability. Results show that task structure predicts reasoning efficiency better than nominal difficulty: sequential inferencechain tasks such as AIME 2025 and LiveCodeBench show high TES, while knowledge-recall tasks such as MMLU-Pro show low TES despite their difficulty. We also find systematic diminishing returns at higher reasoning effort levels, including cases where additional thinking reduces accuracy. Finally, Reasoning Cost Share (RCS) shows that inference spend is often dominated by internal thinking, while Deployment Cost Multiplier (DCM) shows how on-premises deployment can change the economics of otherwise costly reasoning workloads. These findings support a benchmarking-driven model-selection rule: enable reasoning selectively by task type, effort level, and deployment context rather than treating it as a universally beneficial mode.

Retail electricity markets in deregulated systems face significant price volatility and complex interactions with forward and futures products, posing challenges for effective operational decision-making. This study introduces a Causal Graph-Informed Temporal Convolutional Network (CG-TCN), a forecasting architecture that integrates a learned causal graph into a temporal convolutional network via a graph-neural embedding to enhance both forecasting accuracy and interpretability of retail electricity price dynamics. It first applies a multi-resolution decomposition to isolate semiannual, quarterly, and monthly trends from high-frequency fluctuations. A causal graph is then discovered over these components and key covariates, including wholesale forward prices and retail contract attributes such as early termination fees, with domain constraints that preserve causal directionality and exogeneity. The learned causal structure is encoded as an adjacency embedding that conditions the TCN's convolutions and attention, aligning representation learning with causal pathways. Using ten years of daily 12-month fixed-price residential contracts from Ohio's deregulated market, we find that wholesale forward prices primarily determine long-term retail price trends, whereas contract attributes influence short-term fluctuations. CG-TCN consistently outperforms benchmark models, achieving mean absolute percentage errors of 3.08%, 3.82%, and 5.43% for one-, ten-, and fifteen-step-ahead forecasts of daily retail electricity median prices, respectively. By combining predictive performance with interpretability, CG-TCN provides transparent, policy-relevant insight to support market analytics, consumer protection, regulatory oversight, risk assessment and procurement planning in competitive electricity markets.

Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating deployment on constrained edge hardware with field-programmable gate arrays (FPGAs) and microcontrollers. Although combining binarization with pruning promises additional efficiency gains, existing pruning strategies are ill-suited to binarized representations and rarely translate into meaningful hardware savings. We introduce a PyTorch-based, research-oriented framework that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks. The framework enables rapid and reproducible evaluation of state-of-the-art approaches and the fast prototyping of new ones. Leveraging this framework, we propose a novel pruning method that accounts for the relative importance of learned parameters across abstraction levels. Such a global weighting mechanism consistently achieves a superior trade-off between model accuracy and pruning rate, achieving a 70% pruning rate on VGG11 with constant accuracy, while state-of-the-art results reach only 41% in the binarized setting.

Organizations assign documentation work to technical writers, yet the knowledge required to produce it is distributed across developers, managers, and other practitioners. Prior work has established quality criteria for judging "good" documentation, but it has not examined how practitioners bring that expertise to improve documentation quality or the challenges they face in doing so. Through semi-structured interviews with experienced technical writers ($n=31$) from different organizations, our work reveals the individual and collaborative effort required to maintain documentation quality. We identify five distinct stages of the documentation review process: self review, technical review, editorial review, play testing, and post-publication feedback. Each stage draws on practitioners with distinct expertise to address quality across content, presentation, and user experience. Our findings surface organizational and technical challenges writers face in recruiting expert reviewers, navigating development timelines, and contending with tools not specifically designed for documentation workflows. Our work positions documentation review as a crucial yet understudied site of collaborative work and opens new research and design directions for process improvement and tool support.

Energy consumption and climate change have made sustainability critical in Software Engineering (SE), driving the emergence of Green SE. Over the past 15 years, numerous solutions for sustainable software systems have been published by the SE community, offering a rich resource for analyzing the field's evolution. To explore this, we conducted a systematic mapping study of Green SE research published between 2010 and 2024. We collected 390 publications, categorizing them by application domain (e.g., mobile, cloud, AI) and research type (e.g., optimisation study, benchmarking, literature review Additionally, we analyzed a representative subset of 79 papers to classify the key elements-such as hardware, measurement, stability, and replicability-considered during energy measurement experiments. Our findings indicate that SE conferences host the majority of energy-related literature. Notably, Green SE studies surged in popularity starting in 2023, largely driven by AI-related publications. Optimization and benchmarking emerged as the most prevalent research types. Ultimately, we aim to inform the SE community about current approaches to energy concerns, highlight critical experimental practices, and advocate for continued action toward more sustainable software engineering.