Papers

This paper presents an airborne software development approach for manned and unmanned aerial vehicles aimed at reducing inconsistencies across system, model-based functional, and embedded software domains. In environments influenced by standards such as ARP-4754B and DO-178C, these inconsistencies typically stem from insufficient enforcement across domain boundaries rather than missing process definitions. Building on a previously proposed toolchain centered on a relational interface database, we identify recurring failure modes and propose a repository-centered implementation to address them, tailored to small, resource-constrained teams operating without heavyweight process overhead. Each domain is assigned a primary repository with cross-repository references and dedicated CI pipelines that generate, update, and validate the exchanged artifacts. Automated interface updates, differential change notifications, and consistency checks propagate changes with minimal manual effort and surface inconsistencies before the time-consuming code-generation and compilation steps. An initial implementation in an ongoing experimental project is described, with qualitative feedback from its early use.

Professional financial examinations require models to combine domain knowledge, calculation, and judgment, yet no benchmark covers the full CFA and FRM structure under one protocol. We introduce FinExam-10K, to our knowledge the largest reported English benchmark for this setting, with 10,198 expert-reannotated questions spanning CFA Levels I-III and FRM Parts I-II. We release 5,110 questions and sequester 5,088 for a quarterly maintained leaderboard. To separate coverage from local answerability, we report a 10,198-item Full-Coverage Track and a 7,625-item Context-Complete Reasoning Track, which is the primary basis for claims about reasoning from the supplied record. Across 17 models, the best accuracy is 85.29% overall. On the frozen Hard band, the best score is 34.68% on the Full-Coverage Track and 54.57% on the 372 context-complete items. All 17 models share 47 context-complete failures. Function-RAG and FunctionGraph-RAG rescue hundreds of errors but also overturn many correct answers, producing little or negative net gain. A gate trained only on public data decides from the question and initial response when FunctionGraph-RAG should run. On the 5,088 held-out items, the gate invokes FunctionGraph-RAG for 7.9% of questions and improves accuracy from 70.83% to 71.23% (p = .0446).

People naturally chat while collaborating and share personal information (i.e., self-disclose) to build rapport and maintain social connections. As robots are increasingly developed to work with people, the effective use of these social behaviors to enhance engagement and support teamwork becomes ever more important. While prior work has shown that robot-initiated small talk can benefit human-robot collaboration, less is known about how best to design such small talk. In this work, we explore how self-disclosure may be designed to support small talk within a human-robot team—especially when the robot is an industrial manipulator that lacks anthropomorphic cues and performs physical work. We first developed an LLM-driven manipulator capable of partaking in small talk, adopting either a low-disclosure or high-disclosure strategy. We then conducted a user study (N = 50) to investigate how self-disclosure in small talk influences human-robot dynamics. Unexpectedly, participants disclosed more in the low-disclosure condition and reported stronger teaming and coordination than those in the high-disclosure condition. This effect was more pronounced among users with prior experience teaming with robots. These results suggest that increasing robot self-disclosure does not necessarily foster rapport, social connection, or reciprocal disclosure; other factors, such as prior HRI experience, should be considered.

Agitation fluctuates over short time horizons in people living with dementia, yet continuous physiological information for anticipating next-day risk is limited. We assessed whether contactless under-mattress signals from the preceding night inform next-day agitation risk and whether preserving minute-level temporal structure improves performance over conventional nightly summaries. We analyzed 423 patient-nights from 65 subjects in a specialized hospital dementia unit using two under-mattress sensing systems. A unified four-paradigm benchmark compared nightly handcrafted summaries, three-period handcrafted features, full-night sequence modeling, and sliding-window multiple-instance learning. Source-specific preprocessing and five-fold patient-grouped cross-validation were used, with performance estimated from pooled out-of-fold predictions. Evaluation included discrimination, calibration, fixed-threshold metrics, and a comparison of period-signal attribution patterns across two temporal models. Full-night sequence modeling achieved the highest discrimination (AUROC, 0.692; AUPRC, 0.849) and balanced accuracy (0.658). Both minute-level pipelines had higher AUROC than nightly summaries, but differences from three-period handcrafted features were uncertain. Cross-model attribution prioritized activity, heart rate, and respiratory rate during the core overnight period. Calibration remained limited. The preceding night's signals supported modest next-day risk discrimination, with minute-level temporal modeling outperforming nightly summaries. Prospective calibration and external validation are needed before use in individual care decisions. This patient-grouped benchmark identifies contactless overnight sensing as a promising biomedical engineering direction for agitation-risk research in hospitalized dementia cohorts.

A byte-level BPE tokenizer is an ordered list of merge rules, so applying only a prefix yields a vocabulary whose token identifiers are the first rows of the full vocabulary. This prefix nesting allows one language model to operate at several vocabulary sizes, use a control token to indicate the active size, and be deployed at any trained size by slicing its embedding and output head. We pre-registered five claims, including margins, seeds, contrasts, and a stop rule, and trained 30 models with 3.1M- and 10.6M-parameter bodies on 200M tokens each. Slicing is numerically exact: across 76 checks, a sliced model reproduces the restricted full model's logits bit for bit and removes 66% of deployed weights without changing latency. However, the shared model trails a fixed-cap specialist by 3.64% bits per byte at 32k against a 1% margin, and by 2.96% at 8k against a 2% margin. A 2x2 ablation separating the control token from output restriction finds that the token changes performance by +0.07% to +0.13%, with all intervals crossing zero, while output restriction costs +0.47% to +1.19%; the factors are substitutes rather than complements. Multi-cap training nevertheless improves robustness: under typographical noise, the same checkpoint degrades 12.5–15.4 points less in its fine mode and outperforms each fixed-cap specialist at that specialist's vocabulary size. A control with neither cap token nor output restriction is equally robust, attributing this benefit to multi-granularity training rather than conditioning. The per-cap penalty tracks each cap's share of training rows, yielding a falsifiable prediction for future work.

How much matrix rank is required to preserve every bounded value output of normalized softmax attention? We study the unrestricted maximum-row-\(\ell_1\) approximation rank \(r_\varepsilon(A)\), exactly the least rank achieving uniform error over all bounded vector-valued values. Row softmax exposes the intrinsic interaction \(C=P_m(\log A)P_N\), whereas invertible \(Q/K\) gauges leave \(A\) fixed while changing the Euclidean geometry of a chosen query/key factorization. We replace that coordinate-dependent description by a projective residual \(q(C-T)\) and an attained factor-radius size \(\kappa(T)\). For every rank-\(r\) retained interaction with \(\tau(T)<\varepsilon\), we prove $$ r_\varepsilon(A)\le \min\left\{ N,\; C_r\left( 1+\frac{\kappa(T)} {(\varepsilon-\tau(T))^2} \right)^{r/2} \right\}, $$ with the same unknown dimension constant as the underlying weighted Gibbs-row cover. The profile is gauge invariant, termwise no worse than native retained-subspace bounds at the same declared dimension, and has a worst-case sharp \(r/2\) size exponent at fixed \(r\) and \(\varepsilon\). We then measure \(r_\varepsilon(A)\) directly on learned attention using 9,978 certified brackets across BERT, GPT-2, Qwen2.5, and two ViT checkpoints; where certificates do not close, the optimum remains interval-valued. A pre-specified 2,302-cell held-out study further shows that the historical native-coordinate geometry block contains coarse, mostly head-level information but no detectable incremental information beyond a strong calibrated baseline. The new intrinsic descriptor is not evaluated in that study. Together, the theory and measurements distinguish an operator-intrinsic complexity control from a stronger empirical explanation that the learned-head evidence does not support.

Engineering agents that interact with external simulators may need to coordinate design modification with reacquisition of engineering evidence for the modified state. We ask whether first post-edit re-verification changes when explicit verification-cadence guidance is retained versus omitted while verification-relevant state/facts are held constant. Cadence-Guided (CG) retained an instruction to request a new simulation after a substantive modification, whereas Cadence-Omitted (CO) removed that instruction; neither condition used a hard gate. The study therefore measures instruction-conditioned post-edit verification-policy adherence rather than spontaneous recognition that prior evidence has become stale. Using DWSIM as the simulator backend and continuous valve-pressure adjustment, five Alibaba/Qwen models were evaluated on eight synthetic cases; each model-case-condition combination was executed three times via live API calls, yielding 120 evaluation slots per condition. Re-verification was observed in 94/120 CG slots versus 32/120 CO slots; cadence violations occurred in 26/120 versus 87/120; and bounded final success was reached in 95/120 versus 35/120. qwen3.5-35b-a3b showed minimal re-verification (1/24 in CG and 0/24 in CO) and no final success in either condition. Within this bounded protocol, explicit post-edit verification-cadence guidance was associated with more re-verification, fewer cadence violations, and more frequent bounded final success, supporting the treatment of verification cadence as an explicit interaction-protocol component.

Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical Dual Semantic Drift that hinders this process: static drift arising from the rigidity of fixed class embeddings, and dynamic drift stemming from the divergence of generated captions, causing severe semantic misalignment that intensifies the stability-plasticity dilemma. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a caption stream for domain-specific knowledge with a class-anchor stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to leverage the evolving teacher distribution for calibrating teacher-student consistency. Building upon DSSG, we further introduce Prototype Anchor Calibration (PAC), yielding DSSG-PAC, which periodically calibrates prototype anchors and caches them until the next calibration. This design reduces redundant text-side computation while preserving the adaptability of class guidance to the evolving text space. We further establish SFF-DA risk bounds that relate student risk to semantic-teacher quality and teacher–student discrepancy. Extensive experiments demonstrate that DSSG consistently outperforms current state-of-the-art methods across multiple benchmarks, while DSSG-PAC largely preserves its adaptation performance with 18.9% lower total adaptation time. The code is available at https://github.com/mrmenand/DSSG.

Social power plays a fundamental role in shaping human interaction, yet computational studies of power remain limited to narrow linguistic and cultural settings. Existing datasets further lack the demographic and relational depth needed for robust cross-cultural analysis. To address this gap, we introduce a theoretically grounded framework for studying social power in naturalistic multilingual dialogue through movie screenplays. The framework integrates a schema informed by social science theory, a native speaker annotation pipeline refined through pilot studies, and a custom interface for scalable cross-lingual analysis. Using this framework, we constructed an initial corpus containing 15,836 annotated instances from 100 scenes in French and Egyptian Arabic movies. Our analysis reveals strong agreement on observable demographic and contextual attributes, while socially interpretive aspects, such as power asymmetry and intention alignment, remain more contested, highlighting the complexity of social power across cultures. We evaluated 6 Large Language Models (LLMs) and Multimodal LLMs on cross-cultural social power reasoning, finding persistent gaps between human and model agreement in relational and theory-of-mind reasoning. Our work introduces the first extensible multilingual framework for studying social power in dialogues and provides an initial evaluation setting for studying cross-cultural social reasoning.

Electrification of commercial delivery fleets is shifting fleet routing from distance- and time-based optimization toward energy-aware decision-making. Existing sequence models primarily provide deterministic point estimates or limited uncertainty summaries, which do not capture the range of plausible energy-consumption trajectories required for operational decision-making. In this work, we introduce a conditional diffusion framework that generates EV battery-current profiles conditioned on route features such as vehicle velocity and ambient temperature. The model combines a latent conditioning encoder with a temporal 1D U-Net denoising backbone that enables trip-related conditions to be mapped into a shared representation and guides the reverse diffusion process. We evaluate the framework on an open-access commercial EV telemetry dataset containing 12k trips from 9 vehicles. The proposed latent-conditioned diffusion model generates realistic cur- rent trajectories that capture both the dominant temporal envelope and sharp transient events. The model achieves a Wasserstein distance of 0.0029 between generated and measured current distributions below the real vs real reference distance of 0.0085 indicating that generated samples lie within the empirical variability of the test set. We further demonstrate that learned latent conditioning substantially improves performance over direct condition injection, reducing the Wasserstein distance by 89.1% and MAE by 52.8%. This work demonstrates a generative modeling framework for characterizing EV energy consumption under real-world operating conditions, providing an essential foundation for uncertainty-aware fleet planning in large-scale operational settings.

Non-prehensile manipulation offers versatile skills for moving and rearranging heavy or bulky objects, particularly when combined with a mobile manipulation platform. However, both model-based and model-free approaches struggle with the complex hybrid dynamics and the sparsity of the contact in these tasks. To address these challenges, we propose a contact-guided exploration strategy implemented within a Multi-Critic Reinforcement Learning (RL) framework. A dedicated exploration critic is trained with a dense contact-seeking reward that guides the end-effector toward meaningful contact points; its influence is progressively decayed to recover a task-optimal policy. We obtain candidate interaction points from a general-purpose grasping algorithm, enabling the exploration mechanism to generalise across various object geometries. We evaluate the approach on multiple tasks, including box pushing, chair transportation, and a dishwasher opening task. Finally, we validate the chair transportation policy through extensive experiments on a quadrupedal mobile manipulator, demonstrating deployable non-prehensile manipulation in the real world.

China has become the world's largest producer of scientific publications, yet concerns persist that this growth is inflated by excessive domestic citation practices. In this study, we analyze a citation network of over 45 million publications from Web of Science (1980-2025) to investigate China's home citation bias and research impact. Using a network reshuffling null model to control for the structural effect of publication volume, we find that China's home citation bias is less pronounced than commonly assumed and has been steadily declining over the past two decades. Chinese researchers do not exhibit a significantly stronger home citation preference than other major countries, indicating increasing internationalization rather than insularity. Furthermore, using the persistent disruption framework, we show that Chinese papers are converging toward American papers in their capacity to produce paradigm-shifting work. These findings challenge prevailing narratives about Chinese scientific home bias and suggest that China's advances in research impact.

Adapting video vision-language models (VLMs) is computationally expensive because video inputs produce a large number of visual tokens, making both fine-tuning and inference costly. Although visual token compression can reduce this overhead, direct adaptation on compressed inputs often causes semantic drift and noticeable performance degradation. We present Token-Budget Distillation (TBD), a parameter-efficient fine-tuning framework for adapting video VLMs under a fixed token budget. TBD freezes the pretrained backbone, updates only LoRA adapters, and integrates FlashVID-based visual token compression into the video pathway. To preserve full-token semantics under compression, TBD employs a dual-path teacher-student design, where a full-token teacher provides stable supervision and a compressed student is optimized with task loss, answer-region KL distillation, GT-anchored margin distillation, and reliability-aware KD control. This design enables the student to recover the semantic behavior of the full-token model while remaining efficient under aggressive token reduction. We evaluate TBD on three video VLM backbones, including LLaVA-Video, LLaVA-OneVision, and Qwen3-VL-8B-Instruct, across four video understanding benchmarks. TBD consistently outperforms compression-only baselines under both moderate and aggressive compression. On LLaVA-Video at retention ratio R = 10 percent, TBD preserves 97.0 percent of the Vanilla model's average accuracy; on LLaVA-OneVision at R = 10 percent, it achieves an average score of 58.4 and matches 100.0 percent relative accuracy.

We present CheXtriev, a graph-based, anatomy-aware framework for chest radiograph retrieval. Unlike prior methods focussed on global features, our method leverages graph transformers to extract informative features from specific anatomical regions. Furthermore, it captures spatial context and the interplay between anatomical location and findings. This contextualization, grounded in evidence-based anatomy, results in a richer anatomy-aware representation and leads to more accurate, effective and efficient retrieval, particularly for less prevalent findings. CheXtriv outperforms state-of-the-art global and local approaches by 18% to 26% in retrieval accuracy and 11% to 23% in ranking quality. The code is available at https://github.com/cvit-mip/chextriev.

Implicit trace estimation aims to approximate the trace of a matrix or linear operator accessible only through matrix-vector or operator-vector products. In the matrix setting, the Girard-Hutchinson estimator typically requires $\mathcal{O}(\varepsilon^{-2})$ products to achieve accuracy $\varepsilon$, while the variance-reduced Hutch++ algorithm reduces this sample complexity to $\mathcal{O}(\varepsilon^{-1})$ for positive semidefinite matrices. We develop infinite-dimensional analogues of these estimators for positive trace-class operators on separable Hilbert spaces. The idealized estimators use Gaussian random elements whose covariance is determined by the target operator, leading to unbiased operator versions of Girard-Hutchinson and Hutch++. We prove high-probability error bounds analogous to the finite-dimensional matrix results; in particular, idealized infHutch++ achieves $\mathcal{O}(\varepsilon^{-1})$ sample complexity. For practical computation, we introduce truncated implementations that restrict the random samples to finite-dimensional subspaces; for fixed sample budget, we show that truncated infHutch++ converges in distribution to its idealized counterpart as the truncation dimension tends to infinity. Numerical experiments with integral operators, density-of-states approximations, and spectral filtering for a radial Dirac operator show that these truncated estimators can achieve accuracy comparable to the ContHutch++ algorithm by Zvonek, Horning & Townsend while using lower-degree function representations and smaller internal discretizations in chebfun.

Reliable long-horizon time series forecasting is an important yet difficult problem. Trends and seasonality introduce complex temporal structure that challenges learning-based forecasting models. Differencing, which subtracts nearby past values to remove such structure, is the classical remedy, but its reliance on hand-picked orders and periods has kept it largely absent from recent deep architectures. We propose \textbf{\underline{Ada}}ptive \textbf{\underline{R}}eversible \textbf{\underline{Diff}}erencing (AdaRDiff), a generalized differencing approach that uses learnable weights to simplify the series through weighted differencing with previous time instants. This yields stabilized residuals on which forecasting is performed, after which the removed components are restored autoregressively to reconstruct the forecast, capturing trend and seasonality jointly through a single operator. This reconstruction admits a closed-form convolutional expression, which parallelizes on GPU and yields up to $33.7\times$ speedup over the naive recurrence. We furthermore rely on a two-phase training schedule that separates temporal structure discovery from reconstruction learning, as suggested by a theoretical analysis of the gradient when using a linear forecasting model. AdaRDiff attains state-of-the-art forecast accuracy across eight benchmarks spanning electricity, weather, traffic, and energy, at negligible parameter cost. Furthermore, it is designed as a plug-and-play module: integrating AdaRDiff improves eight diverse backbones, from linear models to Transformers, in the large majority of cases, by up to $25.9\%$ with a linear backbone and $18.3\%$ with iTransformer.

A $p$-ary bent partition of $\mathbb{F}_p^n$ is a partition into $K$ nonempty cells such that every balanced assignment of its cells to $\mathbb{F}_p$ produces a bent function. It was asked whether every possible depth $K$ is a power of $p$; for general $p$, previous affirmative results required regularity or cell-symmetry hypotheses. We prove the stronger unconditional statement that, for every nonzero $h$, exactly $p^n/K$ points remain in the same fine cell under translation by $h$. Thus the fine cells form a partitioned difference family and the fine label map is zero-difference balanced. Consequently $K\mid p^n$, so $K=p^t$; nonempty cells further give $1\le t<n$. In even dimension, the classical cell-size theorem yields $K\mid p^{n/2}$. Together with the known odd-dimensional ternary three-fibre parameter restriction, this gives the global bound $t\le\lfloor n/2\rfloor$. The proof is an exact finite average over balanced coarsenings. The main counting identity and selected consequences are formalized and kernel-checked in Lean 4.

Fine-grained credit assignment is a central challenge in reinforcement learning for long horizon LLM agents. Standard objectives often train from programmatically verifiable terminal rewards by broadcasting each sparse outcome to every action in a trajectory. Existing methods typically seek finer credit from the rollout side, constructing auxiliary trajectory signals or additional comparisons to estimate action importance. Although useful, these approaches still treat the verifier that judged success as a scalar reward, discarding its internal task structure. Our key insight is that many verifiable tasks already encode the relevant checks inside their terminal verifier. We propose VICT (VerifierInstrumented Credit Tracing), a training-time interface that exposes executable or evidence backed atoms and traces them back to actions through dependency-valid proof edges. VICT redistributes group-relative advantage only along those edges, shifting credit assignment from rollout-side inference to verifierside tracing. It preserves the original terminal reward, abstains when evidence is incomplete or ambiguous, and changes only the training-time advantage tensor, requiring no learned critic, process labels, branch rollouts, or inference-time verifier access. On ALFWorld and WebShop, VICT improves substantially over outcome-only training and achieves strong performance alongside recent fine-grained credit methods; ablations rule out dense atom rewards, final-commit credit, temporal proximity, and sparsity as sufficient explanations.

Neural audio representation learning has enabled a range of content-oriented applications, but the resulting features remain limited for tasks involving audio processing. Furthermore, it is not obvious what processing-aware representations should capture: the processing itself, abstracted away from source content, or the processed audio that retains it. Existing approaches implicitly commit to one or the other and also differ in their models, data, and evaluation, obscuring which design choices drive their behavior. We address both questions within a unified framework of three objectives: processing consistency, description alignment, and equivariance via forward prediction. We compare all combinations of the objectives under a controlled setup and reveal their relative strengths and interactions. Our framework produces both a transformation embedding and a processed-audio embedding, and we find that the two play complementary roles: distance-based tasks favor the former, while probe-based tasks favor the latter. Combined with improvements in network architecture and training pipeline, our representations outperform prior baselines across retrieval, probe-based evaluation, and style transfer.

Cyber Threat Intelligence (CTI) reports often describe Indicators of Compromise (IoCs) such as IP addresses, URLs, file hashes, and cryptocurrency wallets involved in cyberattacks. Those IoCs are typically described in the unstructured report's text, or listed at the end of the report with little context, limiting their usefulness. This paper presents TagZilla, a platform that, given a threat report, automatically analyzes its text and tags the IoCs it describes with contextual information about the threat group and malware family that the IoC belongs to and the type of abuse associated with the IoC (e.g., phishing, sextortion, command-and-control). TagZilla provides a novel LLM-based approach to assign owner tags to IoCs using an open-world classification, and assigns 29 abuse type tags to IoCs using a closed-world classification. We evaluate TagZilla on a manually generated ground truth of 100 threat reports containing 1,534 indicators, where it achieves an F1 score of 0.94 for owner tagging and 0.93 for abuse type tagging. Then, we apply TagZilla to tag 765 threat reports, identifying 15,583 IoCs belonging to 637 malware families, 113 threat groups, and 162 other entities. The results show that TagZilla can tag IoCs even in reports describing multiple actors and malware families, enabling the generation of IoC profiles for those entities.

We present a novel unfitted computational framework for simulating fully nonlinear potential flow-based water waves. Focusing on wave propagation, we describe the core methodology, which involves a high-order polynomial-corrected shifted-boundary approximation on unfitted spectral elements. This approach allows for the simulation of a curved, highly time-dependent (moving and deforming) free surface affected by bathymetric changes. All that on a simple Cartesian background mesh without re-meshing or further approximations of non-affine geometric features. In addition, we highlight the importance of proper gradient recovery using a polynomial-preserving technique to accurately capture the vertical free-surface velocity. Ultimately, the goal is to develop a high-order convergent numerical scheme capable of simulating highly nonlinear waves over long periods. This is achieved through an arbitrary-order finite-difference approximation of the free surface combined with added hyperviscosity for numerical stability. We present verification and validation test cases for wave propagation in both periodic and finite domains. Emphasis is placed on convergence studies, the justification for using high-order approximations, the importance of optimal gradient recovery, long-time simulation of highly nonlinear waves, and nonlinear wave interactions with both affine and curved bathymetry changes, as well as with vertical walls, for highly nonlinear stream function waves and high-amplitude solitons. The novel computational model offers a comprehensive, all-in-one framework for simulating ocean waves and their interactions with offshore structures. It provides significant geometric flexibility, enabling boundaries such as the free surface to move and deform over time without the need to re-mesh a boundary-fitted mesh.

Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. Their practical impact increasingly depends on whether those pieces can become complete, dependable deliverables. This survey examines agentic artifact creation, which we define as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work. Functionally, the process links an operational representation of the artifact, a construction policy, and runtime verification whose feedback can redirect later actions. We reviewed 259 works available through August 20, 2026: 230 systems meeting this definition and 29 benchmarks of agentic artifact construction. We compare six artifact families, then analyze application settings and evaluation practice as separate dimensions. Across families, construction challenges reflect not only modality but also how tightly decisions are coupled and whether failures become visible while they remain repairable. Decomposition can reduce local complexity while increasing coordination and reassembly costs. Learned judges may add little independent evidence when they share the generator's preferences or blind spots. We formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted repair, and revalidating affected state after change. We also identify opportunities for sustaining coherent, accountable control as artifacts, creator intent, and construction systems evolve. A curated paper list is available at https://github.com/GeminiLight/awesome-agentic-artifact-creation.

Forecast combination is a reliable way to improve predictive performance when several forecasting models are available. Simple aggregation rules such as the mean, median, trimmed mean, inverse-loss weighting, and exponential weighting are often strong baselines, but their relative performance can vary across datasets, forecast horizons, deployment settings, and levels of disagreement among base forecasters. We develop Generalized Gibbs Ensemble Weighting (GGEW), a probabilistic framework that treats forecasting models as experts and assigns ensemble weights using a Gibbs-style exponential transformation of normalized predictive loss. The framework extends this basic weighting rule through numerical stabilization, diversity-aware score corrections, and online hyperparameter adaptation. GGEW produces a family of related methods, including Stable Gibbs weighting, Directional Gibbs-NCL, and Symmetric Gibbs-NCL. These variants share one core algorithm and differ only in the score used inside the exponential weighting rule. For sequential deployment, we adopt a UCB-style bandit mechanism, called online Local-UCB, to adapt the learning rate, diversity strength, and Gibbs variant without evaluating the full hyperparameter grid at every prediction step. We evaluate GGEW on official M4 competition forecast submissions and external rolling-origin deployment experiments using Monash Traffic Hourly, Electricity Hourly, and Solar Weekly datasets. Results suggest that Gibbs-style adaptive weighting is a useful and competitive tool across several benchmark settings, although its relative performance varies across datasets, forecast horizons, deployment protocols, and forecast disagreement groups. The contribution is not a universal dominance claim, but a framework and empirical study motivating further investigation of when adaptive Gibbs-style forecast combination is useful.

REST APIs are widely used in modern software systems, but developers and testers often lack visibility into which parts of an API specification are exercised by a test suite. Traditional coverage analysis usually relies on source-code instrumentation, which is impractical for REST APIs that are distributed, externally maintained, and hence accessible only through black-box execution. This paper presents RESTCov, a lightweight tool that computes structural REST API coverage from an OpenAPI specification and observed HTTP request/response logs, reporting coverage across paths, operations, parameters, media types, status codes, and status classes. RESTCov produces both machine-readable results and a human-readable HTML report, helping users inspect coverage gaps, diagnose specification-log mismatches, and evaluate REST API test suites without requiring access to the implementation. Screencast: https://youtu.be/mNz2P43OyUc Repository: https://github.com/2tolgahan2/RESTCov

The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language model (LLM) inference. NVFP4's micro-block design, such as a group size of 16, offers strong representational flexibility for capturing local weight distributions and isolating outliers, but it also introduces a large and highly sensitive space of per-group scaling factors. Existing post-training quantization (PTQ) methods primarily focus on refining quantized weight values, leaving this scale-selection step underexplored. To address this gap, we propose H-Scale, a lightweight post-processing method for NVFP4 per-group scale refinement. Instead of minimizing plain weight reconstruction error, H-Scale selects hardware-valid group scales using a diagonal second-order proxy derived from calibration activations, thereby targeting layer output perturbation more directly. It is designed as a drop-in replacement for RTN-style scale selection in diverse NVFP4 pipelines, requires only modest offline calibration, and introduces strictly zero overhead at inference time. Under a fixed evaluation protocol, experiments on mainstream LLMs show that H-Scale generally improves a broad range of NVFP4 baselines and brings several variants closer to the BF16 reference.

Microservice architecture supports software evolution by decomposing a system into small, loosely coupled services that can be deployed independently. Contrary to the expectation of high modularity, prior studies have reported that code clones exist across service boundaries, some of which are co-modified in the same version. Such clones may require changes to be propagated across service boundaries, thereby undermining service independence and increasing maintenance costs. However, existing tools do not support microservice-aware clone analysis. We present CC4M, a microservice-aware clone analysis and visualization tool. CC4M detects and enriches clone pairs with service-boundary, co-modification, file-category, and metric information. The enriched clones are visualized in an interactive scatter plot with explicit service boundaries, supporting metric-based filtering to prioritize clones with potentially higher maintenance impact. Using an open-source microservice application, we illustrate how CC4M helps identify the potential impact scope of code changes. A demo video and the tool are available at https://www.youtube.com/watch?v=0xOIQPFbkUg and https://doi.org/10.5281/zenodo.21204195, respectively.

Vision-Language-Action models (VLAs) allow users to specify manipulation tasks in natural language, but distinguishing a target or placement goal among objects of the same category or similar appearance requires detailed expressions that VLAs may not use reliably. We propose DeicticVLA, which canonicalizes Language Instruction (LI), Vision-Language Instruction (VLI), and Visual Instruction (VI) into a text prompt and deictic masks through text-prompt completion and deictic gesture grounding, enabling a single pretrained VLA to handle all three instruction modes. With a shared backbone, demonstrations, and matched training steps, we compare two RGB visual prompting methods, two separate-channel mask prompting methods, and three training strategies in simulation. Under two-stage training, the four prompting methods achieve high in-distribution success but differ in their ability to use deictic masks in unseen layouts. Across methods, training-strategy ablations show that two-stage training improves such use, while retaining second-stage LI data mitigates forgetting without reducing VLI and VI performance. In three real-world tasks, one policy supports all modes. VLI and VI outperform LI under unseen expressions, appearance changes, and novel objects. For unseen categories, both achieve 100% success, compared with 16.7% for jointly trained LI. These results demonstrate the unified three-mode interface and guide DeicticVLA design.

This paper investigates an inverse source problem for a time-fractional diffusion-wave equation with a singular inverse-square potential. The source term is assumed to consist of a known temporal factor and an unknown spatial component, which is to be recovered from terminal-state measurements. The well-posedness and regularity of the forward problem are established within an appropriate energy framework by exploiting Hardy-type inequalities and the spectral properties of the associated singular elliptic operator. The terminal observation operator is then shown to be compact, and uniqueness of the spatial source is established under a suitable nondegeneracy condition on the temporal factor. To stabilize the resulting ill-posed inverse problem, a Tikhonov regularization approach is introduced. The gradient of the regularized functional is derived through an adjoint problem involving a right-sided fractional derivative, leading to an adjoint-based conjugate gradient method with an exact line search for the numerical reconstruction of the unknown source. Numerical experiments are conducted on both one-and two-dimensional spatial domains, using both exact and noisy terminal data, to demonstrate the effectiveness and stability of the proposed source reconstruction method.

Digital design requires predicting how a metal surface will look later in its oxidation; this paper presents such a pipeline for copper. Given a fixed-camera observation, the system forecasts appearance 10 accelerated units ahead and converts it into the albedo, normal, roughness and metallic maps a renderer consumes. Forecasting is evaluated as an authoring tool would use it, on a copper specimen the system has not observed: an entire recording is held out, so training and checkpoint selection use one specimen and the test set is the whole of a second, recorded on a different day and condition. Under this protocol a learned spatio-temporal model with a monotone oxidation state, the most accurate forecaster within a single recording, is less accurate than copying the last observed frame on an unseen specimen, in both directions, as are three further trained architectures. The only forecaster that transfers is a closed-form global color extrapolation with no trained parameters, improving on copy-last-frame by 13.4% and 50.6%, with a margin that increases with horizon to +16.7% and +55.5% at t+10. Two controls qualify this: correcting every frame for the photometric drift measured on a non-oxidizing reference region leaves both margins intact, ruling out uncontrolled exposure as their source, and a moving-block bootstrap over the 6 independent windows each recording contains separates the larger margin from zero but leaves the smaller one not individually significant. The mechanism is measured: a learned susceptibility map encodes where corrosion begins on the training specimen and misleads on a new one, whereas the global color trajectory is what specimens share. The pipeline therefore deploys the closed-form forecaster for unseen specimens and the learned model only for continuing one already observed. Code, splits, protocol and leakage audit are released.

Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current approaches force a trade-off between accuracy and efficiency. Hidden-state probes are fast but limited: they are either not context-aware: operating on a single vector and cannot model interactions across positions; or they are very costly: having dedicated classifier models (Llama Guard, Qwen Guard, LLM-as-judge) or performing computation on hidden states for all tokens and then pooling the results (MultiMax). This shows an intrinsic trade-off between efficiency and accuracy. However, we find that the speculative-decoding module in recent LLMs can be repurposed for efficient high-quality classification. By appending a trained soft prompt at the end of the target sequence, we can repurpose the speculative-decoding module into a sequence classifier. At inference time in a speculative-decoding pipeline, the KV cache is already in GPU memory, so classification adds negligible overhead. We evaluate on four classification tasks across four models (Qwen3.5-4B, 9B, 27B, MiniCPM4.1-8B). Our small probes consistently outperform zero-shot GPT-5.4-mini and, on multilingual prompt safety, match or beat specialized 8B safety classifiers (Qwen3Guard-Gen-8B, Llama-Guard-3-8B) without running a full LLM.