Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (math.PR) 2026-06-16

Sharp connectivity bounds for the vacant set of random interlacements

arXiv:2504.02777v2 Announce Type: replace Abstract: We consider percolation of the vacant set of random interlacements at intensity $u$ in dimensions three and higher, and derive lower bounds on the truncated two-point function for all values of $u>0$. These bounds are sharp up to principal exponential order for all $u$ in dimension three and all $u \neq u_\ast$ in higher dimensions, where $u_*$ refers to the critical parameter of the model, and they match the upper bounds derived in the article arXiv:2503.14497. In dimension three, our results further imply that the truncated two-point function grows at large distances $x$ at a rate that depends on $x$ only through its Euclidean norm, which offers a glimpse of the expected (Euclidean) invariance of the scaling limit at criticality. The rate function is atypical, it incurs a logarithmic correction and comes with an explicit pre-factor that converges to $0$ as the parameter $u$ approaches the critical point $u_*$ from either side. A particular challenge stems from the combined effects of lack of monotonicity due to the truncation in the super-critical phase, and the precise (rotationally invariant) controls we seek, that measure the effects of a certain "harmonic humpback" function. Among others, their derivation relies on rather fine estimates for hitting probabilities of the random walk in arbitrary direction $e$, which witness this invariance at the discrete level, and preclude straightforward applications of projection arguments.

02.
Nature (Science) 2026-06-17

Lethal plague outbreaks in Lake Baikal hunter-gatherers 5,500 years ago

Plague is among the most devastating diseases in human history1. However, early strains of the plague-causing bacterium Yersinia pestis lacked virulence factors that are required for the bubonic form until around 3,800 years ago2,3. Consequently, the morbidity and mortality of early plague strains remain unclear. Here we describe early plague strains that are associated with two phases of outbreaks among mid-Holocene hunter-gatherers near Lake Baikal in southeast Siberia, beginning from about 5,500 years ago. These outbreaks occur across four hunter-gatherer cemeteries, with a 39% detection rate for plague infection. By reconstructing kinship pedigrees, we show that small familial groups were affected, consistent with human-to-human spread of disease, and that the first outbreak occurred within a single generation. The infections appear to have resulted in acute mortality, especially among children (aged 8 to 11 years). We further note functional differences, including in the ypm superantigen locus, which is also present in present day Yersinia pseudotuberculosis. The new strains diverge ancestrally to known Y. pestis and constrain the timing of its emergence, indicating that this happened before approximately 5,700 years ago. These findings show that plague outbreaks happened earlier than previously thought and were indeed lethal. We contend that the occurrence of outbreaks among mid-Holocene hunter-gatherer communities well outside the sphere of Late Neolithic Europe challenges the notion that higher population densities and lifestyle changes during the Neolithic agricultural transition were prerequisites for plague epidemics. Analyses of ancient DNA from hunter-gatherers near Lake Baikal in southeast Siberia around 5,500 years ago indicate that highly virulent Yersinia pestis emerged earlier than previously estimated, far from the next known cases of infection in Late Neolithic Europe.

03.
arXiv (CS.LG) 2026-06-18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606.18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited. We propose signature filtering, a detection-time module that enhances watermark detection without modifying watermark embedding and text generation. It learns a small set of ``signature'' tokens whose presence makes watermark tests unreliable, and removes these tokens before detection. The signatures are obtained by solving a mixed-integer linear program on a small training set, with constraints that maximize the true positive rate. We additionally derive finite-sample and asymptotic bounds under several attacker models (color-blind, color-adaptive, and distributionally correlated). On four well-known watermark families (Kgw, Sweet, Unigram, Exp), four benchmark corpora (C4, MBPP, HumanEval, Code-Search-Net), and six LLMs (Opt-1.3b, Opt-6.7b, Llama2-13b, Llama3.1-8b, Qwen2.5-14b, Phi-3-medium-14b), 2- and 3-gram signatures raise detection rates in weak-signal and low-entropy settings from 8~31% without filtering to 78~99% with filtering, while keeping false positives controllable and often negligible. In stress tests where we scramble sentences and perturb 25~50% of tokens by dilution, deletions, and substitutions, 2-gram filters for Kgw-style watermarks preserve most of the clean-text detection gains, often matching or outperforming the advanced WinMax watermark detector. Signature filtering thus provides a simple, scalable, and model-agnostic add-on to strengthen watermark-based provenance checks for LLM text in information processing workflows.

04.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

05.
arXiv (CS.CV) 2026-06-18

Epipolar Geometry Improves Video Generation Models

Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. We align diffusion models using pairwise epipolar geometry constraints via preference-based optimization, directly addressing unstable trajectories and geometric artifacts through mathematically principled geometric enforcement. Our approach efficiently enforces geometric principles without requiring end-to-end differentiability. Evaluation demonstrates that classical geometric constraints provide more stable optimization signals than modern learned metrics. Training on static scenes with dynamic cameras ensures metric quality while the model generalizes to various dynamic scenes. By bridging data-driven learning with classical computer vision, we reduce epipolar error by 31% and improve human-rated consistency from 54% to 72% without compromising visual quality.

06.
arXiv (CS.AI) 2026-06-25

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation

arXiv:2606.24902v1 Announce Type: cross Abstract: The "First Proof" benchmark [1] posed ten research-level mathematics questions to the strongest publicly available LLMs and found them consistently wrong-not silent, but confidently, fluently wrong. This paper asks why. Working from the per-question post-mortems in First Proof's Appendix A, I identify four failure modes: citation fabrication (F1), premise smuggling (F2), silent problem reformulation (F3), and local-to-global compatibility gaps (F4). I then audit eight one-shot proofs generated by Gemini 2.5 Flash on Questions 1, 2, and 5 of the benchmark, using two instruments built specifically to surface F1 and F2. The central finding is uncomfortable for anyone who sees retrieval-augmented generation (RAG) as the obvious fix: not one of the eight proofs contained a confirmed fabricated citation, yet every single one contained at least one load-bearing claim asserted as a "fundamental result" or "standard argument" with no justification attached. That failure mode-F2, premise smuggling-is invisible to citation verification by design. A premise-audit instrument I introduce flags it at 100% precision (5/5 judge-confirmed flags are true positives) and 50% proof-level recall in this corpus. The taxonomy and the audit together suggest that the right long-term objective is building inference-time pipelines that prevent these failure modes from occurring, not just detecting them after the fact. Index Terms–Large language models, mathematical reasoning, hallucination, premise smuggling, failure-mode taxonomy.

07.
arXiv (CS.CV) 2026-06-16

Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning

Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to entangled content and style features. With a reverse triplet synthesis pipeline to build a million-scale training set and a dual-branch Style-Content DiT (SC-DiT) that decouples style and content via separate ROPE embeddings and causal masking, we observe that such a one-stage training paradigm on mixed style categories causes semantic styles to dominate, hindering texture style learning, and harming content preservation. To address these issues, we propose Style-CCL, a Multi-Stage Curriculum Continual Learning framework that trains SC-DiT from semantic (easy) to texture (hard) styles, and from clean to synthetic data, with Random Memory Rehearsal across stages to avoid catastrophic forgetting. Extensive experiments demonstrate that our Style-CCL achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.

08.
arXiv (CS.CV) 2026-06-15

Rendering-Aware Sparse Sampling for BRDF Acquisition

Accurate BRDF acquisition is essential for realistic rendering, but dense gonioreflectometer measurements are slow and expensive. We study how to select a small set of BRDF measurements that is most informative for reconstructing material appearance under a learned BRDF prior. Existing sparse-acquisition methods often optimize samples for BRDF-space reconstruction for all materials, while the perceptual importance of a adaptive measurement ultimately depends on its effect on each rendered appearance. We therefore formulate sparse adaptive acquisition as a rendering-aware optimization problem. Our method combines a set encoder for sparse coordinate–value observations, a pretrained hypernetwork-based/PCA-based BRDF reconstructor, and a differentiable renderer. During sampler training, the reconstructor remains fixed, and gradients from a rendered-image loss optimize the measurement locations. This separates acquisition design from prior fitting and encourages the sampler to choose directions that are informative under the learned material distribution. To make the comparison controlled, we evaluate the uniform baseline, meta-learning method, HyperBRDF method, and our learned sampler under matched sample numbers, train/test split, rendering scene, object mask, image mapping, and metrics. Our central claim: rendering-aware sampling improves extremely sparse BRDF acquisition when final rendered appearance is the target. BRDF-space and combined losses are reported only as ablations, together with joint refinement and image-only latent fitting for unseen materials.

10.
arXiv (CS.CL) 2026-06-12

The Tone of Awareness: Topic, Sentiment, and Toxicity Maps During Mental Health Month on TikTok

Despite raising concerns about the mental health effects associated with the usage of TikTok, little is known about how related content is framed by creators and received by audiences. We collect the content of 28,341 TikTok videos and 80,130 comments from Mental Health Awareness Month (May) in 2023 and 2024 via the TikTok Research API, and study how the tone of awareness varies across topics and years. We characterize "tone" as the emotional and interpersonal framing of mental health discourse, operationalized through sentiment and toxicity measures. We extract topics from video text using BERTopic and log-odds keywords, then quantify topic-conditioned sentiment (XLM-T) and toxicity (Detoxify) separately for video transcriptions and comments. Sentiment captures the affective valence of content, while toxicity reflects the presence of harmful or abusive language. We find a stable set of recurring themes across years, spanning clinical conditions, emotional disclosure, self-care, and campaign-oriented content, with engagement highly skewed toward a small subset of topics. All sentiment and toxicity analyses are computed separately for video content and comments, allowing us to distinguish between content production and audience reception. Sentiment in videos is often negative for emotionally charged topics, while comments tend to shift toward more mixed or positive polarity, especially for suicide prevention. Toxicity is low in median overall, but exhibits longer-tailed outliers in comments than in videos that are more pronounced in comments and concentrated in specific topics (e.g., "Duet", "Suicide Prevention", and "Psychisch"). Overall, our results provide a topic-level decomposition of mental health discourse on TikTok during awareness-month campaigns.

11.
arXiv (CS.CL) 2026-06-16

Attention, not scale, drives human-AI alignment in multimodal language prediction

Humans routinely draw on visual context to predict upcoming words. To what extent current vision-language models produce comparable behaviour is unclear. Here we placed five state-of-the-art pretrained systems side-by-side with 600 human participants in a web-based Visual-World Paradigm. On each of 100 six-second movie clips, models and participants received either text only or synchronised video and text and judged how likely a specified target word was to appear next; human eye movements were tracked throughout. Adding visual context increased model-human alignment in predictability ratings across all architectures (average Delta r = 0.18) with no impact of parameter size. When visual context was informative, transformer attention significantly increased alignment. Attention maps from two transformer models corresponded with human gaze, explaining up to 70% of the inter-participant variance when the scene contained informative cues. Notably, cross-modal attention reliably tracked anticipatory human fixations on semantic cues. These results suggest that current transformer-based vision-language models can approximate human behaviour exploiting visual context during language prediction - and that selective attention to informative cues, not sheer model scale, is the principal driver of this alignment.

12.
arXiv (CS.CV) 2026-06-16

BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data

Insect classification is important for agricultural management and ecological research, as it directly affects crop health and production. However, this task remains challenging due to the complex characteristics of insects, class imbalance, and large-scale datasets. To address these issues, we propose BioAutoML-NAS, the first BioAutoML model using multimodal data, including images, and metadata, which applies neural architecture search (NAS) for images to automatically learn the best operations for each connection within each cell. Multiple cells are stacked to form the full network, each extracting detailed image feature representations. A multimodal fusion module combines image embeddings with metadata, allowing the model to use both visual and categorical biological information to classify insects. An alternating bi-level optimization training strategy jointly updates network weights and architecture parameters, while zero operations remove less important connections, producing sparse, efficient, and high-performing architectures. Extensive evaluation on the BIOSCAN-5M dataset demonstrates that BioAutoML-NAS achieves 96.81% accuracy, 97.46% precision, 96.81% recall, and a 97.05% F1 score, outperforming state-of-the-art transfer learning, transformer, AutoML, and NAS methods by approximately 16%, 10%, and 8% respectively. Further validation on the Insects-1M dataset obtains 93.25% accuracy, 93.71% precision, 92.74% recall, and a 93.22% F1 score. These results demonstrate that BioAutoML-NAS provides accurate, confident insect classification that supports modern sustainable farming.

13.
arXiv (CS.LG) 2026-06-16

Incentives and Evidence in Learned Service Orchestration

arXiv:2606.16555v1 Announce Type: cross Abstract: Reinforcement learning for service orchestration has been the subject of sustained research for over a decade, yet it is not used in production at scale. The usual explanation is that learned controllers degrade under delayed and noisy telemetry, workload shifts, and uncontrolled tenants. We test whether existing evidence supports that explanation. We evaluate three highly influential RL-based orchestration systems spanning resource allocation, DAG scheduling, and autoscaling, using pre-registered predictions about comparative degradation under production-relevant perturbations and paired inference with family-wise error correction. Across the tests, most predicted performance reversals do not occur. Diagnostic analyses show that these outcomes often reflect comparator collapse, artefact limitations, or evaluation choices rather than evidence that learned controllers tolerate the perturbations. One apparent advantage under observation lag is roughly fortyfold compared to a Kubernetes HPA-equivalent controller. Another widely cited result cannot be reconstructed from its released artefact, and the strongest reproducible margin is far smaller than the published results. Conclusions also reverse under changes in perturbation magnitude and evaluation mode. Based on these results and broader patterns in the literature, we identify an institutional problem. Publication and review incentives favour benchmark gains against convenient comparators, even when those gains provide little evidence of deployment performance. We argue that the problem is not solely technical. Rather, it is institutional, so learned orchestration needs production-grade comparators, registered perturbation models, separate operational metrics, and publication criteria that reward reproducible operational evidence. Without these changes, the literature can grow without establishing whether learning improves orchestration.

14.
arXiv (CS.CL) 2026-06-25

Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models

Dialogue systems based on large language models (LLMs) have advanced significantly in recent years. However, dialectal variation remains a major challenge, particularly for systems that process spoken input. LLM-based speech language models (SLMs), which integrate LLMs with speech processing components, show promise for spoken language tasks, yet their ability to comprehend dialects has not been sufficiently studied. Moreover, it remains unclear how the dialectal understanding of the base LLM affects SLM performance. This study investigates the dialectal robustness of both LLMs and SLMs using Japanese dialects as a test case. We define robustness as the ratio of performance on dialectal versus standard inputs, enabling fair comparisons. Our experiments show that SLM robustness correlates with that of their text-based counterparts. Furthermore, training with dialectal data and fine-tuning the speech encoder each improves robustness in SLMs.

15.
arXiv (CS.CV) 2026-06-25

A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context

Apparent emotion in natural images is often not visible from the face alone. The face may be small, hidden, or neutral, while posture and scene context carry much of the evidence. This work studies context-aware emotion recognition on EMOTIC with an image-only two-stream model. A ResNet-18 body stream encodes the target-person crop, and a CLIP ViT-B/16 scene stream encodes the full image. The fused feature predicts 26 categorical emotion labels and the continuous valence, arousal, and dominance values. This study examines whether small context-debiasing or rare-class training changes still help after adding a CLIP scene encoder. The clean two-stream model is compared with simplified CCIM-style intervention, CLEF-lite context-bias subtraction, ASL tuning, and class-balanced sampling under the same implementation pipeline. No tested variant improves over the clean two-stream model, which achieves 34.52% mAP on the EMOTIC test split. CLIP gives the model broad scene semantics, but the simplified causal, counterfactual, and rare-class changes do not automatically improve performance. Most remaining errors are in rare and subtle emotion categories, so the next step should focus on label relationships and finer subject-context interaction.

16.
arXiv (CS.CV) 2026-06-24

GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence

Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either operate directly in 3D, which ensures geometric consistency but often lacks generative expressiveness, or rely on 2D amodal completion, which provides strong appearance priors but does not guarantee reliable 3D structure. This raises a key question: how can we achieve both generative plausibility and geometric coherence in amodal 3D modeling? To answer this question, we introduce GENA3D (GENarative Amodal 3D), a framework that integrates learned 2D generative priors with explicit 3D geometric reasoning within a conditional 3D generation paradigm. The 2D priors enable the model to plausibly infer diverse occluded content, while the 3D representation enforces multi-view consistency and spatial validity. Our design incorporates a novel View-Wise Cross-Attention for multi-view alignment and a Stereo-Conditioned Cross-Attention to anchor generative predictions in 3D relationships. By combining generative imagination with structural constraints, GENA3D generates complete and coherent 3D objects from limited observations without sacrificing geometric fidelity. Experiments demonstrate that our method outperforms existing approaches in both synthetic and real-world amodal scenarios, highlighting the effectiveness of bridging 2D priors and 3D coherence in generating plausible and geometrically consistent 3D structures in complex environments.

17.
arXiv (CS.AI) 2026-06-18

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization

arXiv:2508.09191v2 Announce Type: replace-cross Abstract: Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent advances, forecasting accuracy remains limited due to the challenge of integrating historical numerical sequences with contextual features, which often comprise unstructured textual data. To address this challenge, we propose TokenCast, a large language model (LLM) driven framework that leverages language-based symbolic representations as a unified intermediary for context-aware time series forecasting. Specifically, TokenCast employs a discrete tokenizer to transform continuous numerical sequences into temporal tokens, enabling structural alignment with language-based inputs. To effectively bridge the semantic gap between modalities, both temporal and contextual tokens are embedded into a shared representation space via a pre-trained LLM, further optimized with generative objectives. Building upon this unified semantic space, the aligned LLM is subsequently fine-tuned in a supervised manner to predict future temporal tokens, which are then decoded back into the original numerical space. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework and highlight its potential as a generative framework for context-aware time series forecasting. The code is available at https://github.com/Xiaoyu-Tao/TokenCast.

18.
arXiv (quant-ph) 2026-06-24

Universal Extraction of Quantum Critical Exponents and Phase Transitions via Tailored Hilbert Space

作者:

arXiv:2606.24312v1 Announce Type: cross Abstract: Finite-size scaling and the renormalization group form the central toolkit for analyzing quantum phase transitions (QPTs). In this Letter, we introduce a novel Hilbert-space tailoring scheme to probe quantum critical phenomena. Applied to the second-order QPT of the one-dimensional (1D) XY model, our method yields precise critical points and exponents on lattices containing merely 50 unit cells. We further establish the universal applicability of this framework via investigations of the Berezinskii-Kosterlitz-Thouless transition in the 1D XXZ chain: critical parameters are recovered with as few as 12 lattice sites. This technique may open an alternative, efficient route to universally characterize QPT across many-body lattice systems.

19.
arXiv (CS.LG) 2026-06-12

The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning

arXiv:2606.13637v1 Announce Type: new Abstract: Catastrophic forgetting is often viewed as the destruction of previously learned knowledge during sequential learning. Building on the Accessibility Collapse framework, we investigate the geometric structure of recoverability in continual learning. Using Split CIFAR-100 and a sequentially trained ResNet-18, we analyze recoverability, representational drift, and recovery complexity across ten tasks. We introduce Recovery Subspace Dimensionality (k_t), a measure of the minimum number of singular directions required to preserve 90 percent of full probe performance. Contrary to our Recoverability Diffusion hypothesis, recovery dimensionality remains stable throughout training (mean k_t = 8.0) despite substantial representational drift. Principal-angle drift strongly predicts recoverability (r = -0.862), and a simple geometric model explains 82.2 percent of recoverability variance. These findings support the Stable Recovery Manifold hypothesis, suggesting that forgotten knowledge remains compactly decodable despite representational reorganization. The results indicate that catastrophic forgetting is primarily an accessibility and manifold-alignment problem rather than information destruction.

20.
arXiv (CS.CL) 2026-06-17

LVLMs and Humans Ground Differently in Referential Communication

For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. We present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We show that LVLMs cannot interactively generate and resolve referring expressions in a way that enables smooth communication, a crucial skill that underlies human language use. We release our corpus of 356 dialogues (89 pairs over 4 rounds each) along with the online pipeline for data collection and the tools for analyzing accuracy, efficiency, and lexical overlap.

21.
arXiv (CS.CL) 2026-06-16

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality into reward signals, but its efficiency depends on whether those criteria reliably capture the task scope and evidence needs. Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency. To obtain more reliable query–rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process: instead of inferring evaluation criteria for a given query, it first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query–rubric pairs from those evaluation targets. Starting from a sampled seed topic, DeepRubric builds an evidence tree by recursively expanding evidence-backed sub-questions, whose leaves serve as atomic and verifiable evaluation targets. It then uses the evidence tree to synthesize the training query and rubrics, ensuring that the reward evaluates exactly the information requested by the query. Using DeepRubric, we construct 9K query–rubric supervision examples and train DeepRubric-8B with rubric-based GRPO, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks with roughly 13x fewer RL GPU-hours.

22.
medRxiv (Medicine) 2026-06-17

Diagnostic Concordance of Immediate Versus 1-Hour Technetium-99m Hydroxydiphosphonate Scintigraphy in Suspected Transthyretin Amyloid Cardiomyopathy

Background Bone-avid tracer myocardial scintigraphy for the diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) has traditionally employed imaging at one or 3-hour intervals. Technetium-99m hydroxydiphosphonate (99mTc-HDP) has unique characteristics that may enable earlier imaging. We investigated the diagnostic concordance of immediate versus 1-hour acquisitions. Methods Consecutive patients with suspected ATTR-CM underwent planar imaging and SPECT/CT immediately and at 1-hour following the administration of 99mTc-HDP. Perugini grades and heart to contralateral lung (H/CL) ratios were assessed. Target-to-background ratios (TBRs) were calculated on the SPECT/CT acquisitions using the left ventricular (LV) septum and three background regions: aorta, LV blood-pool, and vertebrae. We assessed diagnostic concordance using Cohen's Kappa ({kappa}), temporal stability using paired t-tests, and correlation between timepoints using Pearson's coefficient (r). The 1-hour SPECT/CT interpretation served as the protocol reference standard. Results Forty-eight patients (83% male; median age, 80 [73-85] years) were evaluated. One-hour SPECT/CT identified 19 positive and 29 negative cases. Immediate SPECT/CT demonstrated 100% diagnostic concordance with the 1-hour reference standard ({kappa} = 1.000; 95% CI: 1.00 to 1.00; p < 0.001). The LV septum/LV Blood-Pool TBR showed the highest correlation (r = 0.956; 95% CI: 0.922 to 0.975; p < 0.001). The LV Septum/Aorta TBR demonstrated high correlation (r = 0.918; 95% CI: 0.857 to 0.953; p < 0.001) and remained stable in the ATTR-negative cohort (-0.02; 95% CI: -0.08 to 0.04; p = 0.54). Significant decrease in the LV Septum/Vertebrae TBR in the ATTR-negative (-0.55; 95% CI: -0.64 to -0.47; p < 0.001) and ATTR-positive cohorts (-1.14; 95% CI: -1.39 to -0.89; p < 0.001) was observed. Conclusions Immediate 99mTc-HDP SPECT/CT is diagnostically concordant with standard 1-hour protocols. By leveraging SPECT/CT and the favorable kinetics of 99mTc-HDP, immediate-phase imaging can accurately reproduce 1-hour acquisitions in cases of suspected ATTR-CM. This expedited approach may improve nuclear laboratory throughput and patient satisfaction.

23.
arXiv (CS.CV) 2026-06-17

Bayesian Magnetic Resonance Joint Image Reconstruction and Uncertainty Quantification using Sparsity Prior Models and Markov Chain Monte Carlo Sampling

We propose a novel framework for uncertainty quantification using compressed sensing magnetic resonance image reconstruction. The problem is formulated within a Bayesian framework as a linear inverse problem, with prior distributions assigned to the unknown model parameters. Specifically, the image to be reconstructed is assumed to be sparse in a given basis. We develop a general framework applicable to any basis and as examples, we test the sparsity of the image in its (1) spatial gradients using a total variation prior model, and in its (2) wavelet transform. A Markov chain Monte Carlo (MCMC) method, based on a split-and-augmented Gibbs sampler, is then employed to sample from the posterior distribution of the unknown parameters. The non-differentiable conditional distributions are efficiently sampled using a proximal MCMC method. The proposed algorithms are validated on both single-coil and multi-coil datasets using various k-space sub-sampling patterns and ratios. The results demonstrate the superior performance of each proposed approach in reconstructing images compared to its counterpart optimisation-based method. Moreover, our framework effectively quantifies uncertainty, showing a notable correlation between estimated uncertainty maps and error maps computed using ground truth and reconstructed images, compared with existing deep learning-based methods.

24.
arXiv (CS.AI) 2026-06-17

All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Code

arXiv:2606.18168v1 Announce Type: cross Abstract: Software practitioners increasingly use AI coding agents that generate test code alongside production code in open source pull requests (PRs). Recent studies report more than 932,000 agent-authored PRs across more than 116,000 repositories, yet whether their test files contain meaningful verification logic remains underexplored. Test files lacking explicit assertions execute code without verifying behavior, so quality gates based on test-file presence overestimate verification strength. The goal of this paper is to help practitioners assess the verification strength of agent-authored patches by characterizing oracle signals and their link to merge outcomes and review effort. We conduct an empirical study of 86,156 test-file patches from 33,596 agent-authored PRs across 2,807 GitHub repositories produced by five coding agents: OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code. A qualitative analysis of 384 stratified patches informs a syntactic taxonomy of eight oracle signal categories. Applied at scale, 80.2% of test patches contain weak or no explicit oracle signals. While raw merge rates are lower for strong-oracle PRs, a regression analysis adjusting for agent, PR size, repository popularity, task type, and language shows strong oracles significantly improve merge likelihood (OR = 1.28, p < 0.001). Our findings suggest that test file counts substantially overestimate verification strength and that practitioners can adopt oracle-aware quality checks to more accurately evaluate agent-authored contributions.

25.
arXiv (CS.LG) 2026-06-19

MortarBench: Evaluating Mortgage Loan Origination Agents

arXiv:2606.19416v1 Announce Type: new Abstract: Loan origination is the process by which a lender creates a new loan, from application and underwriting through approval and funding. This process serves a critical role in evaluating the eligibility and level of risk posed by an applicant. Recently, firms have begun using mortgage loan agents to augment human loan officers, despite a lack of any public benchmark. To fill this gap, we present MortarBench, a loan origination agent benchmark. MortarBench uses a financial data synthesis and mutation pipeline to generate examples with broad edge case coverage that match real-world distributions and questions. We find that state-of-the-art large language models (LLMs) perform poorly, with closed-source models achieving at most 77.1\% exact match accuracy. We also discover systematic biases in LLM perception of foreignness related to non-English names. Noting these weaknesses, we introduce CRIT, a confidence calibration framework. Our method increases accuracy to 80.5\% while improving risk management steering and reducing bias.