Machine Learning · Cross-listed from stat.ML
Weighted Data Selection: Sharp Upper-Half and Five-Dimensional Laws
Zhongxuan Liu and Hongzhi Wang
How much risk does a small reweighted training support retain? For finite weighted least squares with the minimum-norm learner, we prove the exact law $\Gamma_d(n)=3-n/d$ throughout $\lceil3d/2\rceil\leq n\leq2d-1$. The guarantee covers every observed feature rank and uses selections that preserve the full feature span. Balanced simplex anchors reduce dimension; positive-weight lifting and independent-line compression close the risk bound. Shifted coordinate pairs attain the matching lower bound. The complete
dataset-level upper bound and sharpness construction are verified in Lean 4. At the smaller budget $(d,n)=(5,6)$, we also prove $\Gamma_5(6)=11/5$, matching the simplex-block prediction from $5=3+2$ over arbitrary interacting configurations.
Circuit covers, comparison second moments, and
circuit-plane probabilities give the sharp excess $6/5$, while polar-face geometry resolves shared rank-three
circuits. The general simplex-block frontier connects these laws within the intermediate-budget selection problem.
Read the full abstract ▾
Cryptography and Security
Characterizing and Codifying Malware Sophistication
Angelo Porcella, Zachary Wadhams, Clemente Izurieta et al. (+2 more)
'Sophisticated' is widely used to describe malware, yet it lacks a consistent definition within academic literature. While existing software quality and complexity metrics offer some insight into malware structure, they do not capture the broader
adversarial and operational traits that contribute to real-world threat potential. This paper presents a systematization of existing approaches for assessing malware quality using static binary analysis. We define malware sophistication through a quality-focused lens by reinterpreting select characteristics from the ISO/IEC 25010 software quality standard, including reliability, maintainability, flexibility, and security, and evaluating their applicability to malware binaries. We identify which characteristics are both relevant to malware and measurable through static analysis, forming the basis for future frameworks that consistently assess malware sophistication when source code is unavailable or dynamic execution is infeasible.
Read the full abstract ▾
All authors Angelo Porcella, Zachary Wadhams, Clemente Izurieta, Jonathan Crussell, Ann Marie Reinhold
Computer Vision
DramaAgent: Agentic Storytelling Video Generation
Ting Huang, Biao Wu, Ronghao Chen et al. (+5 more)
Recent
diffusion and autoregressive models have substantially improved text-to-
video generation, yet producing coherent long-form story
videos with consistent characters and aligned audio remains challenging. Existing methods often suffer from narrative drift, unstable character identity, weak cross-scene continuity, and audio-visual mismatch over extended sequences. We propose DramaAgent, a hierarchical, agentic, and model-agnostic framework for long-form text-to-
video-and-audio generation. Rather than improving the underlying
video backbone itself, DramaAgent introduces an upper-level control layer that decomposes generation into story planning, persistent character conditioning, scene-wise synthesis, and reflection-guided targeted repair. The framework maintains reusable story and character states across scenes, diagnoses failures such as identity drift, missing scene semantics, temporal discontinuity, and cross-modal mismatch, and repairs problematic clips in a stage-specific manner. Experiments across multiple
video generation backbones show that DramaAgent improves long-horizon coherence, character consistency, narrative fidelity, and scene-level audio-visual consistency over direct generation and strong baselines. These results suggest that hierarchical agentic control is a practical direction for controllable long-form audiovisual generation. Code: https://github.com/AIGeeksGroup/DramaAgent. Website: https://aigeeksgroup.github.io/DramaAgent.
Read the full abstract ▾
All authors Ting Huang, Biao Wu, Ronghao Chen, Zeyu Zhang, Tengfei Cheng, Qizhen Lan, Huacan Wang, Hao Tang
Computation and Language
FACET at WMT 2026 Automated Translation Quality Evaluation Task
Ahrii Kim, Chanjun Park and Seong-heum Kim
Different error types in machine translation require different evidence. Whether meaning is preserved can be judged only against the source, while whether the target is well-formed, or whether it names one entity consistently, can be judged from the target alone. We present FACET, our reference-free submission to the WMT26 Automated Translation Quality Evaluation Task, which decomposes evaluation into Fluency, Accuracy, and Consistency passes and gives each pass only the context its error type requires. A single fixed model is prompted three times, and the merged error spans yield the three task outputs, error spans, quality scores, and error-free labels, with no trained components. We also submit FACET-C, which omits the Consistency pass. Without gold labels, we characterize the predictions of FACET. Its system rankings place post-edited human translation first, and the Consistency pass changes about a tenth of segment scores while leaving the ranking nearly unchanged.
Read the full abstract ▾
Machine Learning
One Mastery Threshold Does Not Fit All Knowledge Tracing Models
Xianghui Meng, Yujing Zhang and Jionghao Lin
Tutoring systems use mastery thresholds to decide when students can stop practicing and advance, but the same numerical threshold can lead to very different decisions when the underlying knowledge tracing (KT) model changes. We examine six KT models across four public educational
datasets and evaluate 12 thresholds from 0.50 to 0.99 using post-advancement performance, advancement coverage, practice burden, and disparities across prior-performance groups. We also identify thresholds that balance performance, extra practice, and advancement under 30 predefined instructional settings.
Bayesian Knowledge Tracing (BKT) is relatively insensitive to threshold changes, while neural models become much more selective as thresholds increase. This partly reflects different model outputs: BKT estimates latent mastery probability, whereas neural models estimate the probability of a correct next response, so the same cutoff does not represent the same level of mastery. The best-balanced threshold varied substantially across models and settings. In half of the tested settings, neural models and BKT differed by more than 0.10 in their selected thresholds, although this gap became smaller when greater priority was placed on reducing extra practice and allowing more students to advance. Stricter thresholds also did not reliably reduce performance gaps and could disproportionately restrict advancement, with stronger-prior students advancing up to 3.26 times as often as weaker-prior students. These results show that mastery thresholds should be recalibrated when the KT model or instructional priorities change and evaluated by their effects on performance, practice, advancement, and access.
Read the full abstract ▾
Machine Learning
Nous: Learning and Certifying Memory Decisions Before Source Calibration
Pranav Singh
Agent memory systems update state decisions from reports whose reliability may be unknown. Existing analyses of source estimation do not determine when a policy can be learned or its improvement certified without identifying the reporting channel. We study these three tasks using the same observed records. For a specified hidden Markov family with continuous source uncertainty, decision learning and powered certification have quadratic sample complexity, whereas fixed-precision source estimation has quartic complexity. We characterize a sharp identified interval for policy gain under an unknown shared-background channel and derive finite-sample certificates under bounded history dependence and conditional copying. Independently trained witness regions support general history spaces, and disagreement-conditioned
auditing improves power for sparse revisions. For dependent histories, prediction-count-preserving batches cancel the unknown reporting background and admit conditional certificates. A MultiWOZ 2.4 evaluation uses text-processing policies on 1,000 human-written test dialogues with simulated audits. Balanced batches retain 2.26 percentage points of the full candidate's 7.34 percentage-point mean gain and obtain more positive certificates under weak audits. These results establish task-specific information requirements and provide an auditable policy-revision framework for Nous.
Read the full abstract ▾
Cryptography and Security
Safety in Self-Evolving Agents: A Survey
Jiahao Chen, Zhou Feng, Oubo Ma et al. (+28 more)
Large
language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-ended environments, this motivates self-evolving
agents that continually update reusable state-including model parameters,
memories, tool definitions, skills, and workflows-from data, feedback, and accumulated experience. This shift changes the safety problem: once experience becomes reusable state, past events become future causes, and information harmless in one context may later influence decisions with greater persistence, authority, or scope. Self-evolving
agent safety therefore asks not only whether a response is aligned or an action authorized, but whether safety properties survive the accumulation, generalization, and cross-context reuse of locally useful experience. We introduce SAVER, a transition-centered framework in which Substrate locates reusable influence, Adaptation captures how it changes, Violation identifies compromised safety attributes, Exposure marks where failures become observable, and Response assesses containment, repair, or revocation. Our survey reveals that failures need not originate from harmful information: legitimate state can become unsafe when adaptation expands its persistence, authority, or scope beyond the conditions under which it was valid. Existing work provides comparatively strong evidence for admission,
retrieval, activation, exposure, and local containment, but much less for descendant repair and evaluation after adaptation resumes. We therefore argue for longitudinal evaluation that traces unsafe influence to its originating transition, verifies repair across descendants, and tests whether it can re-emerge under continued
evolution.
Read the full abstract ▾
All authors Jiahao Chen, Zhou Feng, Oubo Ma, Yichen Yan, Ruixiao Lin, Hangtao Zhang, Linkang Du, Hengyu An, Yong Yang, Jun Liu, Junhao Li, Naen Xu, Chunyi Zhou, Yuan Su, Zehao Jin, Qianli Ma, Leyi Qi, Yiming Wang, Zhe Ma, Yuwen Pu, Mengyao Du, Yuanyi Song, Enhao Huang, Zhihui Fu, Jun Wang, Jinfeng Li, Yuefeng Chen, Hui Xue, Yiming Li, Tianyu Du, Shouling Ji
Computation and Language
BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL
Chen Shen
Data
agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of columns, so cost constraints may require choosing between table coverage and serialization detail well before the context window is full. We introduce BudgetSchemaBench, an execution-grounded diagnostic for this setting. Its construction derives relevance labels mechanically from gold SQL, without human- or LLM-authored ground truth. Using a pooled 80-database catalog, we sweep four schema-context budgets and compare three representations while keeping each retriever's table ranking fixed. A source-namespace check rejects queries that obtain the correct result from the wrong database. The evaluation covers three conditions: end-to-end
retrieval; frozen-gold, in which the required tables are guaranteed; and a probe that removes those tables. For the primary solver with raw serialization, raising the budget from 2.5% to 50% of the catalog improves execution accuracy on 1,279 held-out questions by 18 percentage points under lexical
retrieval but only 3 under dense
retrieval; the dense retriever already finds most required tables at the smallest budget. When the required tables are removed, 94.6% of correct predictions name one of them exactly, consistent with reconstruction of absent schema from parametric knowledge. For the two main solvers in the frozen-gold condition, the three representations differ by at most 2 percentage points, and the widest paired 95% confidence interval bounds the difference within +/-4 points. We observe the same qualitative patterns with one
reasoning model from a different family. When
retrieval is coverage-limited, execution accuracy is more sensitive to the schema budget than to the tested serializations. The diagnostic and the code used to construct and evaluate it are publicly available.
Read the full abstract ▾
Computation and Language
A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID
Paweł Blicharz and Miłosz Grunwald
AI-generated text detectors achieve high accuracy on standard
benchmarks, yet the internal representations that drive these predictions remain poorly understood. We study which
neurons in a frozen BERT-base-uncased encoder support AI-text detection, using the RAID
benchmark across six generators spanning pure-base and instruction-tuned models. We apply the L1-to-L2 sparse-probing protocol of Gurnee et al. (2023) to all 9,216 CLS hidden-state dimensions (12 layers x 768), which we call
neurons. The procedure recovers a stable set of under 1% of
neurons per generator, consistent across folds and seeds; a probe restricted to that set retains most of the full-feature detection accuracy. Bidirectional activation patching confirms this set's causal relevance: in both directions it flips predictions an order of magnitude more often than size-matched random sets. Mean-ablating the same
neurons leaves accuracy largely intact; the signal is therefore redundantly distributed. Cross-generator analysis reveals a bipartite structure: instruction-tuned generators concentrate 30-36% of stable
neurons in BERT's final layer while both base generators fall below 14%, consistent with a layer-12 footprint of post-training
alignment. Leave-one-family-out evaluation shows the selected
neurons retain 86-94% of the full-feature ceiling on unseen generator families, so a detector can operate on a small fixed subspace without re-identifying
neurons per generator.
Read the full abstract ▾
Machine Learning
When Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator
Phillip Jiang
Short-term
forecasting of cloud-induced power ramps across a network of distributed photovoltaic (PV) or irradiance sensors is a recognised pain point for grid operators. A natural idea is to make the graph neural network (GNN) advection-aware: connect each site to the sites upwind of it, with edge time-lags set by the cloud-motion vector (CMV), so that a ramp is propagated forward before it physically arrives. Using a controlled synthetic testbed with a known wind field, we show that (i) with a realistic cross-correlation CMV estimate, an explicit advection graph does not beat a plain static or learned-adjacency spatiotemporal GNN; (ii) roughly half of the benefit available from a perfect CMV comes simply from providing an accurate motion vector as an input feature, not from graph structure; and (iii) advection helps only when the advective displacement over the forecast horizon, v*H, fits inside the sensor network. Motivated by (ii), we introduce a small self-supervised cloud-motion
estimator – a position-aware encoder trained only on a multi-lag optical-flow reconstruction objective with an annealed kernel – that recovers the true wind vector to 2-4 degrees median angular error, 2-4x better than the classical cross-correlation method across every wind regime. Freezing this
estimator and feeding its vector to the forecaster closes about 60% of the oracle-CMV RMSE gap at moderate wind (8-15% RMSE reduction over no advection), with no external wind data. We also report a negative result for a spatially-coherent probabilistic head. All claims are established on a single synthetic simulator; we discuss why real-network validation is the necessary next step and outline it.
Read the full abstract ▾
Computation and Language
ChainDoRA: Tensor-Train Factorized Weight-Decomposed Low-Rank Adaptation for Parameter-Efficient LLM Fine-Tuning
Ashfak Yeafi, Mehedi Hasan and Md Khairul Islam
Parameter-efficient fine-tuning (PEFT) adapts large
language models (LLMs) to downstream tasks while updating only a small fraction of their pretrained parameters. Low-Rank Adaptation (LoRA) uses two trainable low-rank
matrices, while Weight-Decomposed Low-Rank Adaptation (DoRA) further separates weight magnitude and direction but retains the dense LoRA-style factorization in its directional branch. We propose ChainDoRA, a weight-decomposed adaptation framework that constructs the directional low-rank factors from a connected Tensor-Train (TT) chain, where the adapter rank forms the boundary rank between input- and output-side TT contractions and an independent TT rank controls representation capacity and parameter cost. Under a controlled 15,119-example response-only adaptation setting with LLaMA-7B, ChainDoRA is evaluated against matched LoRA and DoRA baselines on seven commonsense
reasoning benchmarks. ChainDoRA with TT rank 16 achieves a seven-task average accuracy of 72.30%, compared with 69.88% for LoRA and 69.39% for DoRA, while requiring only 5.35M trainable parameters versus 56.10M for LoRA and 56.98M for DoRA, corresponding to a 90.62% reduction relative to DoRA. Ablations over TT rank and adapter placement show controllable parameter-accuracy trade-offs, indicating that connected TT parameterization can substantially reduce the parameter cost of magnitude-direction adaptation while preserving, and in this setting improving, downstream
reasoning performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
Physics-guided deep metric learning with continuous time embeddings for open-world radar pulse de-interleaving
Vikas Agnihotri and Jasleen Kaur
Radar pulse de-interleaving is a foundational Electronic Support Measures (ESM) task that aims to separate chronologically interleaved pulse streams from multiple non-cooperative transmitters under unknown emitter cardinality in dense, contested electromagnetic environments. Classical histogram transforms and closed-world deep classifiers degrade under severe pulse loss, agile Pulse Repeti tion Interval (PRI) modulation, and spurious clutter. In this paper, we systematically characterise continuous temporal representations and physics-guided model selection in deep metric learning for open-world radar de-interleaving. Building on the
transformer-based metric-learning framework for open-world deinterleaving introduced by Gunn et al. [1], we introduce a continuous Time-of-Arrival (ToA) sinusoidal positional encoding that directly models physical inter-pulse durations rather than ordinal
token indices, a design choice that contrasts with [1], who found ordinal positional encodings provided no benefit and omitted them entirely. Neural network parameters are optimised solely via Supervised Contrastive (SupCon) learning, while scale-aware physical domain priors based on PRI Consistency and Angle-of-Arrival (AoA) continuity serve as physics-guided validation and checkpoint-selection criteria operating on unsupervised HDBSCAN cluster assignments.
Read the full abstract ▾
Computation and Language
Graph-Based Inference for Feedback-Driven Word Deduction: A Scalable Framework for the Jotto Problem
Dakshi Arora, Prakhar Kumar Srivastava and Ranjib Banerjee
A feedback-based word deduction framework based on the Jotto problem is proposed, and the problem space is represented as a weighted graph where all valid words correspond to nodes, and the edge weight is defined by the number of common letters between the two words. Finally, the gameplay is defined as an iterative constraint propagation mechanism where feedback is used to iteratively narrow the incompatible space of the graph, facilitating the reduction of the hypothesis space in a structured and interpretable manner. In contrast to existing approaches, where the problem space is typically defined for fixed-length isograms, the proposed framework generalizes to variable-length words (between 3 and 8 letters) and naturally extends to repeated letter cases, facilitating the treatment of realistic Jotto problem instances within a unified framework for the first time. The proposed framework's applicability and solver dynamics are also discussed through an interactive implementation and a qualitative case study, respectively. Significant automated tests on approximately 3,000 simulated gameplay scenarios identify a novel convergence behavior: the expected number of iterations diminishes with increasing word length. A strong relationship is confirmed using statistical tests to verify a logarithmic relationship, which is also verified using regression modeling and goodness-of-fit tests. In addition to the initial problem statement, this formulation introduces graph
pruning as a viable paradigm for feedback-driven inference with interpretability and its association with symbolic
reasoning and interactive intelligent systems.
Read the full abstract ▾
Computation and Language
ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains
Artemis Llabrés, Marc Serra Ortega, Tomàs Ockier et al. (+6 more)
In this report we present results of the ICDAR2026 Competition on
Multimodal Reasoning over Documents in Multiple Domains. This competition aimed to advance research in document understanding through the task of Visual Question Answering (VQA). Building upon previous DocVQA
benchmarks, this competition introduces challenging
reasoning questions over a diverse collection of documents spanning eight domains, including business reports, scientific papers, slides, posters, maps, comics, infographics, and engineering drawings. The competition concluded with 20 valid submissions from 8 teams spanning zero-shot VLMs, OCR and parser-augmented pipelines, agentic
retrieval systems, multi-
agent ensembles, and fine-tuned
multimodal models. The results show that the strongest systems move beyond single-pass prompting and instead rely on structured evidence extraction,
retrieval, verification, and orchestration across multiple components.
Read the full abstract ▾
All authors Artemis Llabrés, Marc Serra Ortega, Tomàs Ockier, Samuel Ortega Cuadra, Amritpal Singh, Christos Georgakilas, Andrey Barsky, Ernest Valveny, Dimosthenis Karatzas
Computer Vision
Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos
Chengguo Zhang and Ping Ping
Camera motion often reflects directorial intent and requires professional equipment, making it a high value form of intellectual property. However, generative
video models can imitate such high value camera motions with simple
prompts, while existing similarity detection methods mainly operate on visual content and fail to capture deeper motion similarity. This is mainly because their training data entangles camera motion with visual content. Moreover, traditional optical flow is insufficient to represent complex camera motions. We therefore build the first
benchmark for camera motion analysis, including a motion
dataset with 11 motion styles and evaluation protocols. Furthermore, we propose a motion representation that augments optical flow with vorticity cues from fluid dynamics, thereby better capturing motions. Experiments show that our detector achieves a 3.02* improvement in plagiarism detection over the strongest baseline and remains effective on generative
videos. We believe our work extends copyright protection beyond static content to dynamic camera motion.
Read the full abstract ▾
Hardware Architecture
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Vishesh Tripathi, Abhay Kumar and Ramsha Khan
The KV cache is a primary bottleneck for
Transformer decoding: its
memory footprint and cache-read traffic grow with sequence length. Grouped-query
attention (GQA) reduces this cost by sharing key-value heads, but still stores both a key and a value at every step. We introduce Grouped Value
Attention (GVA), which stores grouped values and reconstructs content keys with a learned linear map. At inference, the map can be absorbed into the query, eliminating the need to materialize content keys in the intended decode path. A small shared decoupled RoPE channel retains positional information through a separately cached positional key. For the configurations studied, this representation reduces persistent cache scalars by approximately 45-47% relative to matched GQA. At the 350M-parameter scale with 30B FineWeb-Edu
tokens, the 16-dimensional positional variant reaches 44.18 average accuracy across five tasks, compared with 44.36 for GQA and 43.88 for MLA. These results demonstrate near-GQA
benchmark accuracy with a more compact cache representation. To translate this compact representation into faster autoregressive inference, we have developed custom decoding kernels and are currently evaluating their end-to-end inference performance with an open-source release planned soon.
Read the full abstract ▾
Logic in Computer Science
Decoupling Evidence Sources in Paraconsistent Logic: A Generalized PAL2v Framework for Educational Assessment
Arthur Nakamura, David Drummond, Welbert Pereira et al. (+2 more)
Paraconsistent Annotated Logic with two values (PAL2v) annotates a proposition with a pair $(\mu,\lambda)$ of degrees of favorable and unfavorable evidence, drawn from a bilattice whose four extreme points are the values of Belnap and Dunn. In applications, however, the second coordinate is almost always taken to be the complement of the first, and several such annotations are then fused. We show that this practice determines the sign of the degree of contradiction in advance, independently of the data: for aggregation functions $F$ and $G$ the fused degree of contradiction equals $F-G^{d}$, where $G^{d}$ is the De Morgan dual of $G$, so that it vanishes identically when the two are dual, and has a constant sign otherwise. In particular the componentwise minimum used throughout the literature yields only consistent annotations, and the conjunction of annotated logic only exact ones; five of the twelve logical states, contradiction among them, are essentially unreachable by construction. We also give a decision procedure for the twelve states that is provably total, in place of the inequality lists in current use, which assign two states to about half of the non-extreme region. We then propose a construction in which the two coordinates are computed from disjoint families of evidence, show that every logical state is attainable. Educational assessment provides a natural instance, since summative and formative instruments are institutionally distinct: mapping examinations to $\mu$ and disengagement to $\lambda$ makes the degree of contradiction equal to the gap between what a student demonstrates and what that student invests. Simulations over three cohort profiles illustrate the classification.
Read the full abstract ▾
All authors Arthur Nakamura, David Drummond, Welbert Pereira, Gustavo Lahr, Kaique Matias de Andrade Roberto
Computer Vision
Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing
Paolo Fraccaro, Gabby Nyirjesy, Daniela Szwarcman et al. (+19 more)
We present a
multimodal foundation model for lunar remote sensing, pretrained from scratch on SomBench, a geographically partitioned corpus of nearly two million co-registered tile bundles spanning 11 modalities at two spatial scales (1 m/pixel and 100 m/pixel). The model adapts the TerraMind masked-
token architecture with two lunar-specific extensions: acquisition geometry is provided as explicit context, and meter- and hundred-meter-scale tiles are trained jointly so that a single set of weights covers both resolutions. FlexiViT patch
embeddings allow adaptation to different patch sizes without retraining, while modality-wise inputs enable flexible
multimodal fine-tuning. Qualitative generation experiments suggest the model learns meaningful cross-modal correspondences, including terrain derivatives from elevation and illumination-consistent reflectance from geometry. We evaluate on four
benchmarks: crater detection at WAC and NAC scales, irregular mare patch (IMP)
segmentation, and polar ice prospectivity regression. Across tasks, the pretrained model matches or outperforms ImageNet-pretrained baselines and an architecturally identical random-init control. On
multimodal ice prospectivity regression, pretrained variants achieve the best results, while the random-init model outperforms most baselines, suggesting gains arise from both the architecture and pretraining. Label efficiency is notable for WAC crater detection, where the pretrained model trained on 50% of the data exceeds the strongest ImageNet baseline trained on the full
dataset. Among adaptation strategies, LoRA matches or surpasses full fine-tuning on crater detection and IMP
segmentation while using far fewer trainable parameters, whereas full fine-tuning performs best for ice prospectivity regression. We release the pretrained checkpoint,
benchmark datasets, and fine-tuning code to support reproducible lunar AI research.
Read the full abstract ▾
All authors Paolo Fraccaro, Gabby Nyirjesy, Daniela Szwarcman, Himanshu Patil, Vishal Gaur, Rohit Lal, Rachel A. Slank, Geoffrey Dawson, Hiyam Debary, Michael K. Barker, Andrew Annex, Vishnu Viswanathan, Zachary Morse, Ethan I. Schaefer, Nikolaos Dionelis, Ankur Kumar, Campbell D. Watson, Manil Maskey, Rebekah I. Dawson-Rigas, Juan Bernabé-Moreno, Rahul Ramachandran, Sujit Roy
Computer Vision
GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transport
Yefan Wang
Industrial anomaly localization has advanced rapidly with feature-based, reconstruction-based, and
distillation-based methods. Most of these methods score a region by asking how unusual its local appearance or feature representation is with respect to normal training images. This is a strong and practical formulation. In this work, we study a complementary
geometric cue for cases where an abnormal region may still contain locally plausible visual features. Thin scratches, small dents, and disrupted repeated patterns often do not make every local patch individually abnormal; instead, they disturb how nearby features vary and connect across the surface. We propose GaugeDefect, a
geometric method for surface anomaly localization based on the
curvature of feature transport. Given a feature
lattice, we estimate a local feature frame at each node and compute orthogonal transports between neighboring frames. The accumulated transport around a small closed loop gives a holonomy
matrix, whose deviation from identity measures feature-transport
curvature. After calibration on normal training images, unusually large
curvature indicates a local inconsistency in the feature field. The
curvature here is not the physical
curvature of the inspected object, but a representation-space measure of neighborhood inconsistency. This makes the method applicable to curved surfaces, textured materials, and non-planar industrial objects. Its main role is to improve localization of subtle surface disruptions, while often producing sharper responses near defect boundaries as a natural consequence of the
curvature signal.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.geo-ph
Large-scale bioacoustic detection using semantic segmentation: a deep learning framework applied to fin whale calls in ocean-bottom seismometer recordings
Jocelyn Japnanto, Alex A. Saoulis, Miriam Romagosa et al. (+5 more)
Ocean-bottom seismometers (OBS), originally deployed for geophysical research, continuously record low-frequency sound for months to years across broad areas of ocean, offering a largely untapped resource for passive acoustic monitoring (PAM) of baleen whales. Realising this potential requires automated detection methods that operate reliably across the varied conditions in large sensor networks. We present a deep learning semantic
segmentation framework that detects the 20-Hz notes of fin whales (Balaenoptera physalus) in OBS spectrograms, assigning each pixel a probability of belonging to a call and converting the resulting probability maps into time-frequency bounding boxes describing individual detections. We trained the model on hydrophone data from one OBS deployment in the Azores-Madeira-Canaries region and applied it without retraining to vertical-component seismometer data from a second, geographically distinct deployment, showing that a single trained model generalises across sensor types and recording environments. Applied to 378,912 h of recordings from 46 OBS sites, the detector identified 6.3 million calls, forming the largest fin whale call catalogue assembled to date, with high precision (~97%) across both deployments. The resulting catalogue resolves call timing and spectral structure accurately enough to support ecological analyses, revealing coherent seasonal shifts in three persistent inter-note interval (INI) groups across the singing season and basin-scale patterns in calling activity. By transforming existing geophysical infrastructure into a scalable sensing network, our approach substantially expands the spatial and temporal reach of PAM without new hardware investment, offering a transferable framework for tracking other low-frequency vocalising species and informing conservation planning, marine spatial management, and abundance estimation across large scales.
Read the full abstract ▾
All authors Jocelyn Japnanto, Alex A. Saoulis, Miriam Romagosa, Rita Leitão, Gabrielle Arrieta, Mónica A. Silva, Matthew Graham, Ana M. G. Ferreira
Computer Vision
RxScribe Bench: A Multi-Axis Benchmark for Evaluating Vision-Language Models on Indian Outpatient Prescriptions
Somil, Vijay Saini, Vidit Verma et al. (+6 more)
Prescription transcription errors are not interchangeable. A model that fabricates a drug and a model that misreads a legible dose pose very different clinical risks, yet prescription-transcription accuracy is typically reported as a single blended figure that treats the two as equivalent. We introduce RxScribe Bench, a
benchmark for evaluating
vision-
language models on handwritten prescription digitization that decomposes performance into four axes tied to clinical severity, rather than folding everything into a single aggregated score. Given only a prescription image and an output schema, a model produces a structured record, which is then compared field by field against a human-authored ground truth of identical shape, with each field also labeled for visibility and legibility. The four axes isolate distinct failure modes, namely Correctness,
Hallucination, Engagement, and Robustness. The Robustness axis withholds its hard-field results rather than reporting one when the supporting sample falls below a minimum-evidence threshold. We evaluate frontier
vision-
language models on real prescriptions across independent cold runs per image, and find that no single model wins across all four axes.
Read the full abstract ▾
All authors Somil, Vijay Saini, Vidit Verma, Riya, Aastha Batta, Vibhuti Malhotra, Chayan Khetan, Piyush Mittal, Puneet Poonia
Computer Vision
The MODA General Attribute Suite: A Four-Track Evaluation Benchmark for Fashion Attribute Extraction
Arkid Mitra
Fashion attribute extraction is evaluated inconsistently: results are reported as single aggregate numbers across image types that pose different problems, fields that are not visible in an image are scored as ordinary negatives, and the effect of vocabulary mismatch between
datasets is acknowledged but not measured. We release the MODA General Attribute Suite, a four-track
benchmark that keeps these problems separate by construction. Each track (localized garment crops, catalogue product images, applicability-aware full-body photographs, and product text) carries its own frozen test set, input contract, metric, and leakage unit, and the tracks are never averaged. The protocol requires label-blind prediction, SHA-256 commitment of prediction files before any label is opened, a fail-closed scorer, and a 10,000-sample paired cluster bootstrap at each track's natural leakage unit; promotion requires a positive interval on every track rather than a favourable mean. We release the scorers, the split builders, our own prediction files with their hashes for every image-track system in the main results and for runs we lose, and the MODA_NER(V) model checkpoints for three of the four tracks. The text model is not distributed; its
benchmark is. We report baseline results, six interventions that did not improve them, and the limitations of the evidence. On the garment-crop track we also measure how far the headline depends on the
benchmark's own design: the order of the two strongest systems depends on whether fields are micro- or macro-averaged, two thirds of the
cells the protocol judges carry no annotation, and disabling the applicability decision cuts attribute micro-F1 from 0.63 to 0.27, so most of that score rests on absence decisions the source labels cannot adjudicate. This version also corrects one figure in an external comparison that an inference preprocessing defect had affected.
Read the full abstract ▾
Computer Vision
SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Science
Himanshu Patil, Gabby Nyirjesy, Rachel A. Slank et al. (+19 more)
Lunar orbital missions, such as Lunar Reconnaissance Orbiter, Kaguya/SELENE,
Gravity Recovery and Interior Laboratory, and Lunar Prospector, among others, provide rich multi-instrument observations, but their heterogeneity in sampling, projection, and conventions limits reproducible machine learning (ML). We introduce SomBench, a unified, spatially-aligned, ML-ready lunar
dataset aggregating 30+ co-registered layers from ten instruments across four missions, spanning 1 meter to 20 kilometer/pixel and covering 82 degree latitude in 90 Lunar Transverse Mercator zones with two polar stereographic caps. An image-anchored tiling pipeline yields pretraining-ready
multimodal tile views with leakage-safe splits, distributed as netCDF with Parquet catalogs. An application
benchmark suite spans impact processes, volcanic history, and polar volatiles. Baseline experiments with ResNet-50 and SwinV2-B models confirm that each
benchmark task is learnable from the released inputs, establishing reference points for future model development.
Read the full abstract ▾
All authors Himanshu Patil, Gabby Nyirjesy, Rachel A. Slank, Vishal Gaur, Daniela Szwarcman, Paolo Fraccaro, Nikolaos Dionelis, Michael K. Barker, Andrew Annex, Vishnu Viswanathan, Zachary Morse, Ethan I. Schaefer, Hiyam Debary, Ankur Kumar, Rohit Lal, Geoffrey Dawson, Campbell Watson, Rebekah I. Dawson-Rigas, Manil Maskey, Juan Bernabé-Moreno, Rahul Ramachandran, Sujit Roy
Emerging Technologies
E-ALS: Approximation-Potential-Aware E-Graph Rewriting for Approximate Logic Synthesis
Bin Sun, Jianan Mu, Jiaxi Zhang et al. (+4 more)
Approximate logic synthesis (ALS) improves
circuit power, performance, and area by trading exact correctness for bounded functional error. However, existing structural ALS methods largely overlook structural bias: even functionally equivalent netlists can expose markedly different approximation opportunities and lead to substantially different outcomes under the same downstream ALS flow. Our experiments show that this effect can induce final area gaps of up to 42.77%. To unlock this opportunity, we propose E-ALS, an e-graph-based framework for approximation-aware structural search. E-ALS combines Function-Reduced Saturation, an ALS-coupled surrogate, search-based extraction, and budget-guided refinement to identify approximation-friendly equivalent structures. Experiments on well-established arithmetic and logic
benchmarks show that E-ALS achieves additional area reductions of 3.2 and 7.0 percentage points under maximum Hamming-Distance and Error-Distance constraints, respectively. Code is available in https://github.com/ZenuSunB/Ecompile.git.
Read the full abstract ▾
All authors Bin Sun, Jianan Mu, Jiaxi Zhang, Rengang Zhang, Zhiteng Chao, Jing Ye, Huawei Li
Artificial Intelligence · Cross-listed from physics.soc-ph
Assessment of Non-Institutional AI Tool Usage Among Clinicians
Sarah Pungitore and Jarrod Mosier
Generative artificial intelligence (AI) tools are increasingly accessible and have the potential to improve efficiency across clinical workflows. However, clinicians may also use non-institutional AI tools that are not provided, managed, or governed by their healthcare institutions, creating potential concerns related to
privacy, security, accuracy, and clinician-AI interaction. Little is known about how clinicians currently use these tools for work-related tasks. We conducted a descriptive survey of clinicians recruited from the University of Arizona College of Medicine-Tucson and Banner University Medical Center-Tucson between May 20 and June 26, 2026. Participants reported their use of AI tool categories and the frequency with which they used AI for specific tasks across five workload categories: administrative work, clinical work, research, studying/continued education, and teaching. Forty-four respondents completed the survey. Forty-three respondents reported using AI for at least one work-related task during the preceding 6 months. Conversational AI and clinical decision support/diagnostic AI were the most used tool categories, each reported by 28 respondents. Administrative and clinical tasks demonstrated the most frequent use. AI was also used for higher-risk activities, including diagnostic assistance and clinical decision support. Non-institutional AI use was common among surveyed clinicians and extended across a broad range of work-related activities, including tasks with potential implications for clinical
reasoning and patient care. Further research is needed to characterize how clinicians use these tools, how they evaluate AI-generated outputs, and how AI can be safely and effectively integrated into clinical workflows.
Read the full abstract ▾
Artificial Intelligence
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
Mohsen Arjmandi
An agentic coding system couples a
language model to a harness: the tools,
prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnesses tuned to their own models, and practitioners assume the vendor-native pairing solves more tasks. We measure that assumption with paired same-model contrasts on a private, contamination-controlled suite of 256 repository and post-cutoff contest tasks. The same 80 tasks ran under claude-
agent-sdk and under deepagents on claude-opus-4-8, and under the openai-codex SDK and deepagents on gpt-5.5, with gemini-3.5-flash and deepseek-v3.2 as side
cells. 792 of 800 planned runs were graded by an isolated oracle. Neither contrast resolves an average advantage for either harness: -1.25 pp for Opus 4.8 (48.8% vs 50.0%, task-bootstrap 95% CI [-10.0, +7.5]) and +1.25 pp for GPT-5.5 (55.6% vs 54.4%, CI [-4.4, +6.9]). The Opus average combines opposite strata: the native harness trails by 9.0 pp on the 61 repository tasks and leads by 23.7 pp on the 19 contest tasks (label-permutation p = 0.003). The partition was chosen after seeing the data and needs a designed replication. Correctness and completion also separate: 22 of 81 runs cancelled at the wall-clock ceiling had produced a passing patch. Re-priced from raw per-turn usage at frozen list prices, the neutral harness cost 1.3 to 1.6 times as much per solved task on Opus 4.8 and 1.2 times on GPT-5.5. These are observed-usage estimates. On the Anthropic account 58 runs left no usage record, and allocating that spend to either
cell would move the Opus ratio between 0.7 and 2.3, so the billed ordering is unresolved. This revision corrects an August 2026 manuscript whose cost figures rested on a usage-semantics defect in our own telemetry (Section 5.1). We release the orchestrator, grading oracle, reanalysis code and derived aggregates. The tasks stay private.
Read the full abstract ▾
Sound
Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition
Frank Fundel and Alexandra Howard
Passive acoustic monitoring produces far more bat recordings than experts can label. We show that simple model-generated pseudo-labels turn this surplus into effective supervision. We compare pseudo-labeling with other semi-supervised learning methods on an 18-species European corpus using only 10% of its training labels, then transfer the strongest approaches to South African field audio containing nine bat taxa and a nuisance class. Pseudo-labeling outperforms the other semi-supervised learning methods on every European measure, recovering up to 61.5% of the gap to full supervision. It transfers to field audio with gains of 10.69 points in species accuracy and 4.96 points in species macro-F1. We also introduce genus-aware smoothing, which directs uncertain target mass toward congeneric species. Combined with uniform smoothing, it reaches 79.16 species macro-F1, 4.73 points above hard targets. Simple pseudo-labels are therefore highly effective at this ecological data scale, while genus-aware targets inject useful biological structure at no annotation cost. https://code4conservation.github.io/UnlabeledEchoes/
Read the full abstract ▾
Cryptography and Security
Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting
Xu Zhang, Dev Mistry, Xiang Xu et al. (+1 more)
In-context learning (ICL) jailbreaks reveal a critical vulnerability in
multimodal large
language models (MLLMs): harmful demonstrations in the
prompt can induce unsafe outputs without modifying model parameters. Despite extensive empirical evidence, existing work lacks a principled understanding of why such jailbreaks reliably succeed or how their effectiveness scales with context composition. We propose a posterior reweighting framework that models a safety-aligned MLLM as implicitly operating over competing behavioral modes, and interprets in-context demonstrations as inference-time evidence that dynamically shifts the model's posterior preference between safe and harmful behaviors. This view formalizes jailbreak as a process of evidence accumulation, yielding predictive scaling laws with respect to demonstration count, harmful ratio,
adversarial strength, and semantic diversity. Guided by this framework, we introduce a posterior-aware inference-time defense that adaptively injects benign counter-evidence based on estimated risk, effectively suppressing harmful posterior drift while preserving model utility. Compared to existing in-context defenses, our method achieves a significantly improved robustness-utility trade-off under a fixed intervention budget. Together, our results establish posterior reweighting as a unifying and predictive framework for understanding and mitigating ICL jailbreak in MLLMs.
Read the full abstract ▾
All authors Xu Zhang, Dev Mistry, Xiang Xu, Ren Wang
Cryptography and Security
PEARL: A Task-Aware Framework for Evaluating Differentially Private Synthetic Educational Data
Xianghui Meng, Yujing Zhang and Jionghao Lin
Personalized learning systems rely on real learner data, including performance, behavior, and demographic information, but these data are highly
privacy-sensitive. Differentially private (DP) synthetic data can support system development and educational research while reducing exposure of individual learners. Existing evaluations, however, assess
privacy and predictive usefulness separately, without determining whether synthetic learner data remain usable for the intended personalized learning task. We introduce PEARL (
Privacy-Equivalence Audit and Release Ledger), which approves a DP synthetic educational
dataset only when it passes all required checks of validity,
privacy protection, predictive usefulness, and suitability for the intended educational task, while recording why each rejected
dataset fails. Across 96 study settings, each defined by a
dataset, data-generation method,
privacy budget, and random seed, only 12 produced synthetic
datasets that passed all applicable PEARL checks. Many
privacy-protected
datasets were rejected for omitting important outcome groups, such as withdrawn students, or for failing to preserve the order of learning activities.
Fairness analysis further showed that some
datasets passing
privacy and predictive-usefulness checks still yielded unequal at-risk prediction performance across groups defined by disability and socioeconomic background. Moreover, Deep Knowledge Tracing and Self-Attentive Knowledge Tracing learned no meaningful next-response patterns from any tested synthetic knowledge-tracing
dataset, showing that
privacy protection alone does not guarantee usefulness for dropout prediction, knowledge tracing, or adaptive tutoring.
Read the full abstract ▾
Cryptography and Security
Black-Box Membership Inference via Word-Level Probability Estimation
Shengjie Niu, Yeheng Ge and Jian Huang
Membership inference attacks (MIAs) have emerged as critical tools for
auditing privacy risks in large
language models (LLMs), aiming to determine whether a given text was included in a model's training corpus. However, most existing MIAs require access to per-
token logits or probabilities, making them inapplicable in practice to proprietary LLMs that expose only textual continuations. To address this underexplored setting, we propose Word-level Probability MIA (WPMIA), a statistically principled MIA for strict black-box
privacy auditing. WPMIA estimates word-level generation probabilities via Monte Carlo sampling with local kernel smoothing, then aggregates these estimates into a sequence-level likelihood
estimator. Furthermore, WPMIA constructs the likelihood conditioned on different prefixes, thereby amplifying the distributional differences between members and non-members. We evaluate WPMIA across various open-source LLMs and find that it consistently outperforms existing black-box baselines. Importantly, we also evaluate WPMIA on modern proprietary LLMs, including GPT-5-Chat, Gemini-2.5-Flash, and Claude-4.5-Haiku, achieving an average TPR@5%FPR of 42.0 across these models. These results offer a sound foundation for future research on strict black-box membership inference. Code is available at \href{https://github.com/niusj03/WPMIA}{https://github.com/niusj03/WPMIA}.
Read the full abstract ▾