Artificial Intelligence
When Big Data Becomes a Curse: Spatial Heterogeneity and the Limits of Learning from Passive Acoustic Monitoring Data
Gabriel Spadon, Wayne Renaud and Priyanka Aravindan
Passive Acoustic Monitoring produces large archives whose recordings are clustered by deployment, season, station identifier, and acquisition configuration. We analyze 908,072 AIS-labeled 679-second recordings from 38 deployments, 20 Atlantic Canadian station identifiers, and 21 receiver positions. The AIS-contact prior varies by more than 200-fold, and per-deployment screening distributions require local interpretation. Bidirectional cross-season transfer over the 18 station identifiers observed in both seasons predicts station identity above the 5.56% uniform-chance level, with balanced accuracy of 15.9% for AIS-contact and 16.4% for no-AIS-contact recordings. The same descriptors predict the two hydrophone models at 74.1% and 85.6% balanced accuracy, respectively, but hydrophone model is strongly confounded with season and other deployment-level acquisition differences. On a retrospectively screened and capped
benchmark of 54m507 recordings, repeated station-grouped holdout yields an ROC-AUC of 0.612 with a station-bootstrap 95% interval of 0.582 to 0.648, compared with 0.661 under a random-window diagnostic. Their paired difference is 0.049 (0.040 to 0.056). Removing raw energy changes unseen-station ROC-AUC from 0.612 to 0.603, while an exploratory training-station scale analysis is non-monotonic. These results show that random-window validation overstates transfer to unseen station identifiers in this corpus. They support dependence-aware validation and broader independent spatial sampling, while spatial-expert models remain a hypothesis rather than an established remedy.
Read the full abstract ▾
Artificial Intelligence
DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents
Abhay Chaturvedi, Shreya Bhattacharya, Rashmika Gopalkrishnan et al. (+1 more)
As
agent capabilities have grown, practical limitations increasingly stem from constrained context windows rather than model capacity. Common strategies, such as truncation, heuristic aging, and lossy summarization, may discard useful information or introduce
hallucination risk. To address these challenges, we propose Dynamic Tool Output Compression (DTOC), a framework for scalable context management in LLM-based
agents that models context updates as explicit and reversible operations within the
agent reasoning loop. DTOC retains full tool outputs in external
memory while inserting compact placeholders into the active context, enabling selective reconstruction when needed. We formalize the DTOC mechanism, integrate it into a ReAct-style
agent architecture, and provide a production-oriented implementation supporting on-demand restoration of compressed outputs. Experiments on DeepSWE reveal model-dependent effects: for responsive models (Sonnet 4.6, GPT-5.4), DTOC reduces input
tokens (10.3 and 12.7%) and
agent steps (2.4 and 32.3%), while increasing solve rates (2.5 and 1.5 times higher) and lowering cost per solved task (3 and 3.5 times lower cost per solved task). For the other models results are more mixed, with GPT-5.5 doubling solve rate and halving cost, but no impact on solve rate and negative impact on cost for the other models. Ablation results show reversibility is critical: disable-only compression variants degraded performance, while full DTOC recovered baseline accuracy at substantially lower context cost. These findings indicate that explicit, reversible context management can improve the efficiency of long-horizon
agent reasoning without degrading task performance.
Read the full abstract ▾
All authors Abhay Chaturvedi, Shreya Bhattacharya, Rashmika Gopalkrishnan, Peter van der Putten
Artificial Intelligence
FusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion
Qiang Chen, Xiao Wang, Qingquan Yang et al. (+5 more)
With the growing global demand for energy,
nuclear fusion has emerged as a promising direction for future clean energy. Tokamaks represent one of the leading approaches to
magnetic-confinement fusion. Achieving high-performance, long-pulse, and steady-state operation requires effective diagnosis of
plasma states. However, existing intelligent diagnostic methods are largely limited to either
multimodal single-task or unimodal multitask learning, while a unified
multimodal multitask learning framework remains underexplored. To address this gap, we construct EAST-VTD640, a
multimodal multitask
dataset that integrates
vision and time-series diagnostics from 640 EAST shots for disruption prediction, edge-localized mode (ELM) recognition, and H98 regression. On this basis, we present FusionMMT, the first unified
multimodal multitask framework for intelligent tokamak
plasma diagnostics. FusionMMT employs multi-scale, time-aware, and variable-aware modeling to handle heterogeneous sampling rates and the high computational cost of high-frequency sequences. It further combines task-adaptive
multimodal fusion with progressive multitask optimization to learn shared and task-specific representations while mitigating cross-task conflicts and optimization imbalance. Extensive experiments on EAST-VTD640 show that FusionMMT outperforms representative
multimodal multitask methods across disruption prediction, ELM recognition, and H98 regression. The source code will be released on https://github.com/Event-AHU/OpenFusion
Read the full abstract ▾
All authors Qiang Chen, Xiao Wang, Qingquan Yang, Hao Si, Zikang Yan, Meiwen Chen, Guosheng Xu, Jin Tang
Artificial Intelligence
Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran et al. (+2 more)
It is challenging to detect hate
speech in Low Resource
Languages (LRLs) because of the absence of annotated data, the informality of its
language structure, and the lack of standardized grammar. A good example of such a challenge is Roman Urdu which is broadly used by South Asians on social media and has a high variation while lacking contextually consistent spellings. The objective of this paper is to conduct a comprehensive assessment of Large
Language Models (LLMs) for Hate
Speech Detection (HSD) in Roman Urdu script and fine-tune these models using the Parameter-Efficient Fine-Tuning (PEFT) method called Low-Rank Adaptation (LoRA). To evaluate zero-shot inference, we benchmarked it against PEFT on different
transformer models, including Mistral, LLaMA, Falcon, and
multilingual BERT. Experiments are conducted on the PURUTT (Parallel Urdu and Roman Urdu Corpus for Toxic Comments and Transliteration)
dataset with over 72,000 annotated comments. The results suggest that zero shot models perform moderately (F1 = 0.56), but updating a small fraction of the model trainable parameters improves the classification performance significantly (F1 > 0.93). Our results have shown that PEFT delivers outstanding performance alongside excellent computational efficiency, making it highly suitable for low-resource
language processing tasks.
Read the full abstract ▾
All authors Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran, Hafiz Hassan Saeed, Rana Fayyaz Ahmad
Artificial Intelligence
Research Assistant: AstraZeneca's Agentic System for R&D
Piotr Grabowski, Mohamed Alameen, Jorge Bretones et al. (+16 more)
We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions across a broad range of data sources. The system provides a chat-style interface that brings together evidence from scientific literature, knowledge graphs, chemistry, clinical trials, safety resources, expression data, and internal experimental systems. It supports both a fast mode for direct question answering and a multi-step mode for more complex research tasks. Responses are grounded in retrieved evidence and linked back to the original sources, allowing users to review and further explore the underlying data. In this technical note, we outline the system architecture, the main design choices behind the product, and lessons learned from deploying it at scale to support day-to-day R&D workflows across AstraZeneca.
Read the full abstract ▾
All authors Piotr Grabowski, Mohamed Alameen, Jorge Bretones, Sabina Cardell, Miguel Carmona, Gavin Edwards, Ben Grainger, Sameh Hassan, Erik Jansson, Artur Kuziakhmetov, Albert Maristany, Hebatallah Mohamed, Andriy Nikolov, Sebastian Nilsson, Mark O'Donoghue, James Pacileo, Ashiq Sultan, Alex Voegele, Michael Ughetto
Artificial Intelligence
Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures
Bongseok Kim, Suman Chakraborty, Gary Huang et al. (+3 more)
Accurate prediction of vapor–
liquid equilibrium (VLE) for hydrocarbon-nitrogen mixtures remains challenging for cubic equations of state, particularly across broad ranges of composition and hydrocarbon chain length. While deep learning models can provide accurate predictions, they often lack interpretability and explicit analytical expressions. In this work, we propose a symbolic machine learning approach to discover interpretable symbolic corrections to Peng-Robinson equation-of-state (PR-EOS) predictions from experimental data. The proposed approach adopts a two-level strategy: symbolic expressions are first identified for individual hydrocarbon systems, after which their coefficients are represented as functions of carbon number to enable accurate prediction across different hydrocarbon systems. The results demonstrate significantly improved prediction accuracy over the original PR-EOS across all hydrocarbon-nitrogen systems. Overall, the proposed approach provides an interpretable symbolic correction framework for improving PR-EOS predictions of hydrocarbon-nitrogen VLE.
Read the full abstract ▾
All authors Bongseok Kim, Suman Chakraborty, Gary Huang, Mehek Mathur, Guang Lin, Li Qiao
Artificial Intelligence
MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis
Yuhua Wen, Yingying Zhou, Qifei Li et al. (+4 more)
Most existing
multimodal sentiment analysis approaches assume access to complete
multimodal inputs. However, real-world applications frequently encounter incomplete or corrupted modalities, posing a critical challenge. Although several methods have been proposed to tackle this issue, they mainly rely on data imputation and heuristic coordination constraints, which fail to effectively extract and leverage task-relevant information from the incomplete
multimodal data. To address this challenge, we propose a unified framework termed Mutual Information Disentanglement with uncertainty-Aware fuSion (MIDAS), which effectively restructures
multimodal representations under incomplete conditions. MIDAS adopts a variational modeling strategy to represent each modality with multivariate Gaussian latent variables and further decomposes them into shared and exclusive factors. To obtain reliable representations, we design a minimax objective that minimizes the mutual information between shared and exclusive spaces for stable disentanglement, while maximizing the mutual information among shared spaces across modalities to enhance semantic
alignment. In addition, an uncertainty-aware fusion mechanism is introduced, where posterior variance is leveraged as a reliability indicator to adaptively weight latent features during fusion, ensuring robust integration even when modalities are incomplete. Extensive experiments on three widely used
datasets show that MIDAS achieves strong and consistent performance gains over competitive baselines across a wide range of incomplete settings, demonstrating its effectiveness and robustness for incomplete data scenarios.
Read the full abstract ▾
All authors Yuhua Wen, Yingying Zhou, Qifei Li, Yingming Gao, Zhengqi Wen, Jianhua Tao, Ya Li
Artificial Intelligence · Cross-listed from stat.AP
Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Screening Assays
Xiaohua Douglas Zhang
High-throughput screening (HTS) assays are central to early-stage drug discovery but are often limited by extreme data sparsity, as primary screens typically use only a single replicate per test substance. This sparsity makes conventional machine-learning performance metrics, such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC), difficult to estimate empirically because they require adequately sized labeled samples. Here, we introduce a model-based framework that derives these classification metrics from the strictly standardized mean difference (SSMD), a well-established HTS effect-size parameter. Under a Gaussian equal-variance assumption, we derive closed-form relationships linking SSMD to Youden-optimal sensitivity and specificity, and sensitivity at a preset specificity, yielding explicit
estimators and exact confidence intervals from the noncentral t-distribution, even under single-replicate designs. Unlike classical statistical power, which approaches 1 as sample size grows regardless of how small the true non-zero difference between group means is, the SSMD-derived sensitivity converges to a finite population value that reflects the true degree of separation between two groups, making it a more meaningful and stable performance measure for hit selection. We demonstrate the utility of this framework in a hepatitis C virus primary siRNA screen comprising approximately 22,000 single-replicate measurements, showing that SSMD, AUROC, and sensitivity-based thresholds yield equivalent and interpretable hit sets. This work bridges classical HTS statistics and machine-learning evaluation theory, providing a statistically principled, reproducible way to estimate classification performance in ultra-low-replication screening workflows.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Enhanced Real-Time 6-DOF Extended Reality Catheter Tracking for Evaluating Potential Improvement in Efficiency, Precision, and Depth Perception for Cardiac Interventions
Mohsen Annabestani, Sandhya Sriram, Andrew Kuzemczak et al. (+3 more)
Despite advances in 3D ultrasound, most percutaneous cardiac interventions still rely on 2D visualization, limiting depth perception and spatial understanding. To address this challenge, we developed an Extended Reality (XR)-based platform that enables real-time six-degree-of-freedom (6-DOF) catheter tracking and visualization within a patient-specific 3D heart model. The system combines a custom machine-
vision algorithm for 5-DOF catheter tracking with a 3D-printed electromechanical encoder that measures catheter roll, providing complete 6-DOF motion reconstruction. In a proof-of-concept study, 20 novice medical students navigated an intracardiac echocardiography (ICE) catheter to six anatomical targets using either immersive 3D visualization or a conventional 2D cathlab-style view. Participants in the 3D condition completed the task in 54.6 seconds and traveled 1,939 mm on average, compared with 267.5 seconds and 7,854 mm in the 2D condition. Therefore, the XR-based 3D system was more than 5x faster and required ~5x less catheter travel. The 3D mode also improved targeting precision and reduced performance variability. Participants consistently rated immersive visualization higher for accuracy, speed, usability, and clinical value. Kinematic analysis showed smoother depth-axis
navigation in 3D, whereas 2D users relied on repeated corrective movements. These findings demonstrate that XR-based visualization can substantially improve procedural training efficiency, precision, and motor control.
Read the full abstract ▾
All authors Mohsen Annabestani, Sandhya Sriram, Andrew Kuzemczak, S. Chiu Wong, Alexandros Sigaras, Bobak Mosadegh
Artificial Intelligence · Cross-listed from cs.CL
Scaling Inherently Interpretable Language Models
Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail et al. (+7 more)
Interpretability is often treated as a tax on capability:
language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult to establish. In this work, we challenge this premise. Rather than reverse-engineering a model, we make interpretability a constraint of the training pipeline, optimized alongside the
language modeling objective. Across three orders of magnitude of compute, on both autoregressive and
diffusion language models, interpretability scales with capability rather than against it. Surprisingly, model representations become more disentangled and aligned with human-understandable concepts with scale. We instantiate the training-time recipe with Steerling-8B, a
diffusion language model with a causal
attention mask. For any group of generated
tokens, Steerling-8B attributes the output to relevant input
tokens, human-understandable concepts, and training data. This enables closed-loop intervention: diagnose an output through its concept or feature attribution, retrieve similar training data, and correct the behavior through concept steering without retraining. Steerling-8B remains competitive with open peer models trained on substantially 2-16x more compute, suggesting a different scaling paradigm: interpretability can be designed into training, and it improves with scale.
Read the full abstract ▾
All authors Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail, Giang Nguyen, Isaac Plant, Muawiz Chaudhary, Nathaniel Monson, Saqib Azim, Zhichen Guo, Julius Adebayo
Artificial Intelligence · Cross-listed from cs.RO
SoRoMoX: Fast, Differentiable, and Parallelizable Soft Robot Models
Maximilian Stölzle, Solange Gribonval, Daniel Feliu-Talegon et al. (+9 more)
Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-
robot control. Their implementations, however, do not support the differentiable, GPU-parallel, and control-oriented workflows that underpin advanced rigid-robotics applications. Here, we fill this gap with SoRoMoX (Soft
Robot Models in JAX), a fully numerical, JIT-compilable Python/JAX framework. SoRoMoX implements articulated, Piecewise Constant Strain, and Variable Strain models through a unified, control-ready interface that provides inertia
matrices, gravitational and elastic forces, Jacobians, and their derivatives. To our knowledge, it is the first rod/strain-based soft-
robot modeling framework that runs directly on GPUs, with Warp kernels accelerating parallel continuum-model execution, and is end-to-end differentiable with respect to states, inputs, and parameters. Sequential CPU rollouts are up to 27.0 times faster than SoRoSim, while GPU-parallel GVS rollouts increase throughput by up to 679.7 times. This performance enables workflows that were previously impractical or impossible: static-
equilibrium system identification with 66% lower marker RMSE; residual-force learning with a further 64% reduction; computed-torque tracking with RMSE reduced by a factor of approximately 500 relative to model-free PD; control-gain optimization with up to 98% lower loss than untuned gains; safety-constrained control using high-order control barrier functions to keep the peak contact force within a prescribed 5 N bound, compared with 33.5 N without the safety constraint; and reinforcement-learning policy training up to 7 times faster than a CPU PyElastica discrete-rod baseline through massively parallel rollouts.
Read the full abstract ▾
All authors Maximilian Stölzle, Solange Gribonval, Daniel Feliu-Talegon, Vito Daniele Perfetta, Michele Martini, Chuhan Zhang, Kiwan Wong, Mohammed Tarnini, Anup Teejo Mathew, Federico Renda, Daniela Rus, Cosimo Della Santina
Artificial Intelligence · Cross-listed from cs.SE
Characterizing the Quality Profile of AI-Generated C++ in Production
Michael Tran, Fred Lewis, Kun Yang et al. (+5 more)
The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off, revealing persistent challenges with code quality and maintainability. Industry leaders, including frontier AI labs, echo these concerns. As large
language models are increasingly relied upon to author production code, understanding their impact on shipped software quality has become a critical priority. However, assessing these effects in industrial workflows remains difficult due to observability barriers. We study the impact of AI-generated code on production quality within a large enterprise operating global products relied upon by billions of users daily. Driven by this scale and user trust, the organization values code quality and has built thorough observability for every line of code deployed into production, enabling us to overcome measurement barriers to assess these effects. This study presents a large-scale empirical analysis of AI-generated C++ code from April 2025 to April 2026, tracking 3.52 million code changes across this enterprise's brownfield codebase. The core purpose is to understand the quality, performance, and maintenance characteristics of AI-generated code compared to human-written code in a production environment at scale. We find that AI-generated C++ code has a distinct quality profile, showing higher rates of interface and coupling burdens, copy and allocation overheads, and a reliance on explicit loops over optimized standard APIs. These issues translate into tangible downstream costs, including increased review effort and a 5-8% increase in compute resource consumption. However, we demonstrate that providing models with targeted, taxonomy-informed feedback can mitigate these effects, leading to an 11.1% reduction in targeted static analysis warnings and improved computational efficiency.
Read the full abstract ▾
All authors Michael Tran, Fred Lewis, Kun Yang, Saksham Thakur, Aditya Kini, Aditya Patil, Milad Hashemi, Parthasarathy Ranganathan
Artificial Intelligence · Cross-listed from cs.SD
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
Jakub Poćwiardowski and Mateusz Modrzejewski
Mechanistic interpretability of music generation has concentrated on audio models, leaving symbolic models largely unexplored. We analyze two public text-to-MIDI systems of contrasting design: the purpose-built encoder–decoder text2midi and MIDI-LLM, a Llama~3.2~1B model extended with MIDI
tokens using linear probing, the logit and tuned lenses, activation patching and difference-in-means steering. Across these methods, we recover musically meaningful structure and show how architecture shapes its formation and control. Pitch, instrumentation, harmony and texture are linearly decodable in both models. text2midi refines predictions gradually across depth, whereas MIDI-LLM works largely in its inherited textual basis before a sharp late rotation into the musical vocabulary; patching identifies a matching late attenuation of
prompt-driven instrument transfer. Steering produces bidirectional changes in register and polyphony in both systems, and in tempo/energy in MIDI-LLM. Our two-orientation protocol isolates directional control and shows that all-layer interventions are robust in text2midi but accumulate disruptively in MIDI-LLM. Together, the results provide a practical toolkit for tracing and controlling musical concepts in symbolic generators. Audio examples are available on a demo website.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning
Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan and Kazi Aminul Islam
Robust aggregation methods are widely used in
federated learning to mitigate the impact of
adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority under the assumption that benign updates form a compact cluster. However, these methods rely on
geometric properties that can be exploited by adaptive adversaries. We introduce the Krum-Proxy attack, a selection-aware
backdoor injection strategy that consistently bypasses Byzantine-robust aggregation. Rather than relying on naive scaling or constraining, our method actively optimizes malicious updates to infiltrate the dense core of the benign distribution. The proposed method constructs
adversarial updates that are not only similar to benign updates but are also optimized to lie in regions of the update space that are favored during aggregation. This is achieved through a two-stage optimization procedure that separates task-specific attack objectives from geometry-aware refinement, using a nearest-neighbor proxy,
stochastic reference modeling, and anchor-guided
alignment. To maintain stealth, we introduce a projection mechanism that constrains
adversarial updates within realistic norm and variance bounds. Experiments on standard
federated learning
benchmarks show that Krum-Proxy achieves higher attack success while preserving clean accuracy, highlighting the vulnerability of distance-based aggregation to selection-aware adversaries.
Read the full abstract ▾
Artificial Intelligence
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
Ziyun Xu, Bosen Ding, Yue Zhang et al. (+10 more)
Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., clicks, dwell time) rather than explicit, natural
language inputs. As a result, users experience a persistent discrepancy between their explicit interests and what passive behavioral
algorithms deliver, limiting their ability to express nuanced preferences or steer their feed in real time. To address this growing gap between how recommendations are optimized and how users wish to articulate their interests, we present Shape Your Feed (SYF), an LLM-based agentic recommendation framework that enables real-time,
multimodal co-curation of content. SYF employs a three-tier architecture: (i) a Perception Flow that captures fine-grained user intent from text
prompts, voice commands, and UI interactions; (ii) a Serving Flow that performs real-time agentic re-ranking and
pruning of candidate items, grounded in a persistent Semantic Profile encoding evolving user preferences; and (iii) a Self-
Evolution Flow that aligns system behavior with human judgments via Direct Preference Optimization (DPO) and an LLM-as-a-Judge ensemble. Offline evaluations show that SYF's
alignment scoring module achieves 98.85% accuracy, substantially improving over strong few-shot baselines. Large-scale online A/B experiments on production traffic further demonstrate that SYF improves feed relevance and user sentiment, indicating a practical and scalable path toward interactive, user-steerable recommendation in industrial settings.
Read the full abstract ▾
All authors Ziyun Xu, Bosen Ding, Yue Zhang, Ji Qi, Qingyuan Song, Jizhou Huang, Liwei Wang, Jefferey Santelli, Yue Weng, Qichao Que, Zhenheng Yang, Junfeng Pan, Linhong Zhu
Artificial Intelligence · Cross-listed from cs.LG
Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separation
Chunhui Shi and Xinwen Fu
Cryptanalytic extraction has been demonstrated for ReLU networks, for networks using componentwise activations such as GELU or SiLU, and for a
Transformer's final projection
matrix. These methods do not recover the bias-free Gated Linear Unit (GLU) feed-forward blocks used in many modern
language models. Such a block multiplies an activated linear projection by a second learned linear projection within each hidden unit, a two-branch structure absent from the network classes and final-layer setting addressed by those methods. We give a constructive, multi-stage forward-query recovery primitive for isolated bias-free GLU blocks. Finite-difference
curvature supplies gate-direction candidates, and paired observations at x and -x separate gate magnitude, orientation, and value-branch coupling. Across high-precision targets, six Qwen layers, an 8,192-unit Llama subproblem, and a full-dimensional Gemma block all reach sub-percent median validation error. Four finite-precision configurations remain below 5 percent median error, but none reproduces every stored weight. These isolated-block experiments are not an end-to-end model-API attack: deriving the required internal block responses from final model outputs remains unsolved.
Read the full abstract ▾
Artificial Intelligence
NxN E-valuation: Hypothesis Certification via a Conformal CRT Null
Bin Wang, Yan Zhong, Zhengyu Zhang et al. (+3 more)
Language models now propose hypotheses faster than anyone can check them, so the step that certifies them must need nothing from the proposer but the hypothesis. We state three requirements for such a step – per-hypothesis automatable, attributable and diagnostic – and introduce NxN e-valuation, which meets them. A hypothesis names a scope, the units it is about, and gives each of them a restriction that scores its outcome. The units of one scope serve as nulls for one another, so no resampling model is written per hypothesis; the
algorithm certifies a stable, scope-level association and reports whether the scope, the restriction, or which unit receives which restriction carries the prediction. For independently drawn units, betting e-values bound the chance of a false certificate for each hypothesis in finite samples, under stated nulls. A betting lower bound on the share of units that carry the association gates every certificate, and an asymptotically valid equivalence test calls the restrictions shared only when it rejects differences between them above a declared noise ceiling. We test it on planted data, on randomized intervention data, and on real purchase data with 285 hypotheses that
language models wrote without knowing our method or our classes, labeled by human experts. Meeting all three requirements costs no accuracy: NxN makes 692 correct decisions in 693 with one false certificate, against 659 with four for a composite of CRT tests that returns our verdicts but needs a resampling model per hypothesis, and 224 with 468 for held-out validation. Removing any of our statistics merges a verdict that certifies with one that rejects. The certificates concern predictive association, not causality.
Read the full abstract ▾
All authors Bin Wang, Yan Zhong, Zhengyu Zhang, Liang Luo, Buyun Zhang, Ellie Wen
Artificial Intelligence · Cross-listed from cs.CL
Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval
Linhai Ma, Ethan F. Wei, Xueqing Peng et al. (+3 more)
Large-taxonomy
retrieval often assumes that the input already expresses the target concept. In many settings, however, the input is indirect evidence, such as a table
cell whose meaning depends on its row, column, datatype, and context. We call this mismatch the
retrieval readiness gap. Our analysis shows that the current index retrieves the target reliably when its semantics are explicit, while raw evidence often leaves it deep in the ranking. We propose Factorized Hypothesis Search (FHS), which maintains multiple partial interpretations over named semantic dimensions. These hypotheses support structured query rendering, multi-hypothesis
retrieval, and dimension-level candidate verification. On both financial taxonomy tagging and CodiEsp clinical coding tasks, FHS achieves the best Recall@1, MRR, and final accuracy among the non-oracle methods. Replacing the factorized hypothesis path with a free-text ensemble causes the largest drop in head-ranking performance, while sequential refinement provides no additional gain over FHS's strong parallel first round.
Read the full abstract ▾
All authors Linhai Ma, Ethan F. Wei, Xueqing Peng, Yan Wang, Lingfei Qian, Víctor Gutiérrez-Basulto
Artificial Intelligence · Cross-listed from cs.CV
Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness
Julia Anna Mielcarz, Daniel Klaaby and Mostafa Mehdipour Ghazi
Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood. We present a controlled evaluation of representation robustness across five pretrained 3D encoders spanning different architectures, objectives, pretraining domains, and
dataset scales. Using BraTS-Africa cases with four MRI sequences, we generate seven frequency- and image-domain artifacts at five predefined corruption settings. Robustness is assessed using linear centered kernel
alignment (CKA), RankMe, and UMAP, complemented by an independent
segmentation-consistency analysis. We find that robustness is strongly model- and artifact-dependent. 3DINO exhibits the most consistently stable representations, while BrainIAC is highly sensitive to several corruptions; NeuroVFM, BrainFM, and Neuro-SimCLR show intermediate but distinct artifact-specific profiles. Across many conditions, CKA decreases substantially while RankMe remains comparatively stable, indicating that artifacts often distort representation geometry without causing dimensional collapse.
Segmentation consistency also degrades under corruption, particularly for ghosting and Rician noise, but aligns only partially with representation-level robustness. These findings show that larger-scale or domain-specific pretraining alone does not guarantee artifact invariance and motivate explicit robustness evaluation before deploying 3D foundation models in heterogeneous MRI settings.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
SLED: Scalable Location Encoding via Distillation
Kevin Lane, Zhongying Wang, Esther Rolf et al. (+1 more)
The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the
planet, but the sheer size of the Earth Observations (EO), differing modalities, and different sensor types pose significant challenges in doing so. Location encoders have emerged as an efficient way of compressing EOs into location-specific
embeddings. However, current state-of-the-art location encoders rely on computationally expensive CLIP-style frameworks that require large batch sizes in the 16K–32K range, suffer from false negative samples, and scale poorly with additional modalities. We introduce the Scalable Location Encoder via
Distillation (SLED), a
distillation-based location encoder that uses geospatial location as a binding modality to pretrain location encoders with any modality of geospatial data. The resulting location encoder framework is lightweight, modular, and can flexibly incorporate multiple modes, while eliminating the need for spatiotemporal coregistration of samples. SLED is performant with batch sizes as small as 128, enabling pretraining at a fraction of the runtime and compute costs of current state-of-the-art models. We demonstrate our approach by pretraining unimodal and
multimodal SLED models on Sentinel-1, Sentinel-2, and Landsat imagery. We show that both unimodal and
multimodal SLED models keep pace with or outperform existing approaches on a diverse set of 19 human-centric
benchmark tasks and explore the benefits of using additional modes in pretraining.
Read the full abstract ▾
All authors Kevin Lane, Zhongying Wang, Esther Rolf, Morteza Karimzadeh
Artificial Intelligence
Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques
Hotaka Maeda and Yikai Lu
Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testing of the items under evaluation. We aimed to build a near-comprehensive AIE model by predicting item acceptance and rejection from item text using historical rejection data from a large-scale standardized testing program. The
dataset contained 52,759 English
language arts (ELA) and mathematics items with 34% permanently rejected from future operational use. Rejection reasons included poor psychometric properties, content issues, bias and sensitivity concerns, and non-content issues. We fine-tuned a DeBERTaV3-large classifier on raw item text, a second DeBERTa classifier on Qwen3-generated item critiques, and a fusion model combining representations from both. The fusion model achieved the strongest overall performance (Accuracy = .75, F1 = .64, AUC = .80, Sensitivity = .64, Specificity = .81). Prediction for math (F1 = .73, AUC = .86) was considerably more accurate than ELA (F1 = .51, AUC = .72). Lowering the decision threshold from .5 to .25 raised average sensitivity for ELA and math to .88 and .91, while reducing specificity to .31 and .56, respectively, which may be preferable in automated item generation contexts where generating items is cheaper than evaluating them. Incorporating item critiques alongside raw item text improved performance across most rejection reasons. The model assigned higher rejection probabilities to more difficult items. However, the fusion model struggled to identify items flagged for bias, sensitivity,
fairness, or accessibility, especially for ELA. These findings suggest that text-based AIE is feasible in some areas and may offer a practical tool for reducing the burden of manual review and field testing, while also underscoring the importance of human review for items with
fairness concerns.
Read the full abstract ▾