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 (quant-ph) 2026-06-12

Quantum optical photoelectron interferometry

arXiv:2606.13447v1 Announce Type: new Abstract: We present a general theoretical framework for multiphoton processes driven by quantum light fields, establishing a direct link between photon statistics and photoelectron observables. Our results show that the autocorrelation and cross-correlation functions, which quantify the underlying photon statistics, are directly mapped onto the resulting photoelectron spectra. Although our framework is broadly applicable, we demonstrate specifically in the example of reconstruction of attosecond beating by interference of two-photon transitions (RABBIT) the influence of the light statistical properties. In this approach, the amplitude, contrast and phase of the oscillations of the sideband signal as a function of pump-probe delay reveal the quantum nature of light. We analyze these observables across several quantum configurations, including correlated infrared and harmonic modes, as well as the uncorrelated case with non-classical harmonic statistics, thereby establishing a general framework for quantum-light RABBIT spectroscopy. We compare the analytical theory with numerical simulations for the case of classical harmonics and an infrared field in a squeezed coherent state, obtaining excellent agreement. Our results reveal how the interplay between classical and quantum correlations dictates the coherence of the photoemission process, providing a new window into the quantum-optical foundations of attosecond science.

02.
arXiv (CS.CL) 2026-06-19

Source-Grounded Data Generation for Text-to-JSON Learning

From financial filings to clinical records, legacy industries rely heavily on long, unstructured documents to store high-value information. Reliably extracting this information into structured, machine-readable representations is a key prerequisite to making the contents accessible to automated systems. JSON is a natural target for such structured extraction, yet constructing reliable and scalable text-to-JSON training data remains challenging. To address this gap, we propose STAGE (Spreadsheet-grounded Text-to-JSON Artifact GEneration), a source-grounded data generation pipeline that constructs reports and JSON schema by using LLMs for scalable synthesis while validating ground-truth values against the underlying spreadsheet. Evaluations on STAGE-Eval, our source-grounded benchmark with an 851-example test set, show that STAGE produces stronger training data than existing approaches. This improves Qwen3-4B exact match from 31.37% to 74.27% and value accuracy from 45.46% to 90.69%.

03.
medRxiv (Medicine) 2026-06-22

Brain-gut axis imaging, motion correction with 11C-carfentanil total-body PET

Background: Mu-opioid receptors (MORs) are expressed throughout the body including in the brain and gastrointestinal (GI) tract. Total-body PET imaging of the brain and GI tract offers a promising approach for cross-sectional in vivo evaluation of the MOR brain-GI axis. However, intestinal motility and bladder filling introduce motion throughout the GI tract over the scan window. Here we establish analysis methodology to account for motion for dynamic imaging of the brain-GI axis, to further characterize peripheral MORs throughout the body and provide a framework for semi-automatic total-body PET modeling. Methods: 4 subjects underwent 90-min dynamic [11C]-carfentanil (cfn) total-body PET acquisitions at baseline, after intravenous naloxone (central antagonist) administration, and after orally administered loperamide (peripheral agonist and P-glycoprotein substrate). Thalamic MOR availability was measured using the Logan reference tissue model. Using CT-based segmentation, the GI tract was subdivided into anatomical segments, in addition to other peripheral organs (e.g., liver, psoas muscle). Frame-by-frame semi-automatic motion correction was performed with three distinct reference frames (11-14 min post-injection, p.i., 35-40 min p.i., and 85-90 min p.i.). The performance of these three were compared to manual correction. Compartment modeling and Logan graphical analysis were performed to estimate relevant kinetic parameters (K1, VT, VTLogan). Results: Across the 4 subjects and regions, kinetic parameter estimates were highly correlated (r>0.7) for K1, VT and VT Logan when comparing semi-automatic (reference frame at 35-40 min p.i.) and manual correction. With semi-automatic motion correction, graphical-based estimation of VTLogan in the gastrointestinal tract was significantly decreased with loperamide relative to baseline (p

04.
arXiv (CS.AI) 2026-06-11

Agentic Software: How AI Agents Are Restructuring the Software Paradigm

作者:

arXiv:2606.05608v2 Announce Type: replace-cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents – systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource – constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users – with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

05.
arXiv (CS.AI) 2026-06-16

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion

arXiv:2601.19697v2 Announce Type: replace-cross Abstract: Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation (RAG) approaches have shown promise by retrieving relevant code snippets as cross-file context, they suffer from two fundamental problems: misalignment between the query and the target code in the retrieval process, and the inability of existing retrieval methods to effectively utilize the inference information. To address these challenges, we propose AlignCoder, a repository-level code completion framework that introduces a query enhancement mechanism and a reinforcement learning based retriever training method. Our approach generates multiple candidate completions to construct an enhanced query that bridges the semantic gap between the initial query and the target code. Additionally, we employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval. We evaluate AlignCoder on two widely-used benchmarks (CrossCodeEval and RepoEval) across five backbone code LLMs, demonstrating an 18.1% improvement in EM score compared to baselines on the CrossCodeEval benchmark. The results show that our framework achieves superior performance and exhibits high generalizability across various code LLMs and programming languages.

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

LoLA: Low-Rank Linear Attention With Sparse Caching

The per-token cost of transformer inference scales with context length, preventing its application to lifelong in-context learning. Linear attention is an efficient alternative that maintains a constant memory footprint, even on infinite context lengths. While this is a potential candidate for lifelong learning, it falls short in memory capacity. In this paper, we propose LoLA, a training-free augmentation to linear attention that boosts associative recall. LoLA distributes past key-value pairs from context into three memory systems: (i) recent pairs in a local sliding window cache; (ii) difficult-to-memorize pairs in a sparse, global cache; and (iii) generic pairs in the recurrent hidden state of linear attention. We show through ablations that our self-recall error metric is crucial to efficiently manage long-term associative memories. On pass-key retrieval tasks, LoLA improves the base model's performance from 0.6% to 97.4% accuracy. This is achieved with a 4.6x smaller cache than Llama-3.1 8B on 4K context length. LoLA also outperforms other 1B and 8B parameter subquadratic models on zero-shot commonsense reasoning tasks.

07.
arXiv (CS.AI) 2026-06-25

TheoremGraph: Bridging Formal and Informal Mathematics

arXiv:2606.25363v1 Announce Type: cross Abstract: Mathematical knowledge is organized around statements and their dependencies, but this structure is exposed unevenly: informal papers cite mostly at the document level, while formal libraries record fine-grained dependencies over a much smaller body of mathematics. We introduce TheoremGraph, a unified statement-level dependency graph spanning both informal and formal mathematics. On the informal side, we parse 11.7M theorem-like environments from mathematics arXiv and recover 18.3M candidate directed dependencies, each labeled by the extractor that proposed it so downstream users can trade coverage for precision. On the formal side, we release LeanGraph, a Lean 4 elaborator-level extractor producing 388,105 declaration nodes and 11.3M typed edges across 25 Lean projects. We bridge the two graphs by embedding generated natural-language slogans into a shared semantic space, linking related statements across papers and across the informal/formal divide; an LLM judge affirms 47,952 such matches above a 0.8 cosine floor, with the judge-acceptance rate rising from 48% across the floor to 87% in the >=0.9 tier. On formal concept retrieval, our name-and-signature representation with graph expansion comes within 0.5pp of LeanSearch v2's reranked Recall@10 (0.775 vs. 0.780) without an LM reranker. We release the dataset, extractors, HTTP API, and MCP interface as infrastructure for mathematical search, attribution, and retrieval-augmented reasoning, available at theoremsearch.com and huggingface.co/datasets/uw-math-ai/theorem-matching.

08.
arXiv (CS.LG) 2026-06-25

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

arXiv:2606.26094v1 Announce Type: new Abstract: For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve with the ability to design controlled experiments? We introduce RevengeBench, a benchmark of 75 LLM generated, Elo-calibrated policies across five game environments, drawn from CodeClash tournament trajectories. The learner observes the hidden target policy play against sampled opponents and designs behavioral probes in the form of custom opponent policies that elicit informative behavior. It then submits an executable hypothesis, which is evaluated using continuous action-distance metrics. We further validate that recovered code carries informative signal in downstream player-versus-player tournaments. Across twelve frontier LLMs, recovery quality varies substantially (34 to 72% of initial distance closed), with reconstructed policies yielding measurable competitive advantage, particularly for weaker models that otherwise struggle to design effective counter-strategies. Our benchmark positions behavioral recovery of programmatic policies as a tractable inverse problem in code-space, opening a path to opponent modeling, policy interpretability, and the broader question of inferring latent mechanisms from observations.

09.
arXiv (CS.CL) 2026-06-24

Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs

Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers – lexical, embedding, and BERTScore baselines alongside entailment/grounding-trained models (clean and FEVER NLI, the checker MiniCheck) – across three evaluation constructs (provenance/topicality, generated-answer attribution, and fact-check entailment), asking whether any scorer transfers: stays within the 95% confidence interval of the best audited scorer on every dataset of a multi-dataset construct. In the construct with the most multi-dataset human-labeled coverage – generated-answer attribution (AttributionBench's four source datasets, n = 1,610, with independent HAGRID, n = 2,150) – none does: the per-dataset metric rankings invert (Kendall tau = -0.64, p = 0.031 on AttributedQA vs. LFQA), and an off-the-shelf NLI scorer that is best on short-claim AttributedQA (AUROC 0.90) collapses to AUROC 0.53 (chance) on long-form LFQA, where BERTScore wins (0.91); the flip is not a length or truncation artifact. This instability has a concrete decision cost: a naive "best-on-average" rule for choosing an evaluator fails leave-one-dataset-out (mean held-out regret 0.172 AUROC, worse than fixing one scorer), so metric choice must be validated on the target dataset rather than learned from others. A prompt-based LLM judge avoids the chance-level collapses the automatic scorers suffer (no LFQA collapse) but is not uniformly best, ~100x costlier, and non-deterministic – relocating, not removing, the validation burden.

11.
medRxiv (Medicine) 2026-06-10

A Three-Tier Operational Benchmark for Evaluating Large Language Models on Hospital Medication Safety

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.

12.
arXiv (CS.LG) 2026-06-18

A Neural Network Framework for Geodesic-Like Curve Computation on Parametric Surfaces

arXiv:2606.18759v1 Announce Type: cross Abstract: The concept of geodesic-like curves was introduced by Chen in 2010 as a method for estimating shortest paths (geodesics) on parametric surfaces, with its convergence established theoretically. However, an efficient numerical computational framework has not yet been developed. In this paper, we propose an elegant and efficient approach for computing geodesic-like curves by leveraging deep learning and Physics-Informed Neural Networks (PINNs). Under the proposed framework, not only can single parametric surfaces be handled efficiently, but a broad class of complex parametric surfaces including multi-surface systems with $C^0$ or higher continuity and surfaces of revolution can also be robustly addressed.

13.
arXiv (CS.AI) 2026-06-24

Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback

arXiv:2606.24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors. The most effective defenses against this are (i) transparency through explainability and (ii) alignment via human feedback. While both show promising results, no publicly available framework currently combines them. To address this, we introduce Themis, an XAI-enabled testing and evaluation framework for Reinforcement Learning from Human Feedback. Themis supports over 200 widely used environments and is easily configurable for experiments in RL, transparency, and alignment. Our results show that Themis can train reward models that match or outperform the environment's true reward signal using human preferences. We also provide a cloud-based platform for collecting human feedback and managing experiments. It is user-friendly, auto-scalable, and supports large participant groups across multiple experiments without extra development overhead. Tests show Themis can support one thousand users in back-to-back experiments on a modest commercial machine.

14.
arXiv (CS.LG) 2026-06-24

An Agnostic Machine Learning Model of Photosynthetic Habitability

arXiv:2606.24458v1 Announce Type: cross Abstract: The search for exoplanet biosignatures is guided by whether planetary environments can sustain photosynthesis. As such, the Photosynthetic Habitable Zone (PHZ) was recently proposed, as the overlap between the canonical habitable zone and the orbital range where stellar irradiance is sufficient to drive photosynthesis. Existing PHZ estimates rely on empirical light-response curves from Earth phytoplankton, and thus include implicit Earth-centric biases. We introduce an agnostic PHZ derived from a generalized model of photosynthesis grounded in thermodynamics and redox chemistry, without reference to model organisms. The model is built on a generic photochemical reaction in which photon capture couples oxidation of a donor molecule to the reduction of CO2. The optical properties and CO2 reduction rate are optimized against irradiance spectra for exoplanets orbiting main-sequence stars, using a genetic algorithm that mimics evolution by natural selection. Our simulations predict that photosynthetic organisms compensate for reduced flux by evolving larger light-harvesting structures. As a result, photosynthetic viability declines only linearly with orbital distance, despite stellar flux falling off quadratically. As such, the agnostic PHZ expands well beyond previous Earth-based estimates. Earth-like (visible light) oxygenic photosynthesis is flux-limited at the outer habitable zone for cool M-dwarf stars; however, both anoxygenic photosynthesis and a hypothetical, NIR-driven oxygenic photosynthesis are viable across the entire habitable zone for M, K, and G stars. This implies that M-dwarf exoplanets could sustain robust oxygenic photosynthesis, though it would be different to that found on Earth, presenting reflectance biosignatures in the NIR band rather than the visible.

15.
arXiv (CS.AI) 2026-06-24

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

arXiv:2605.08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes of these failure modes with a mechanistic analysis focusing on the decoder-based VLMs. We trace these failure modes to a geometric over-alignment: to bridge the modality gap required by attention mechanisms, decoder-based VLMs over-align visual embeddings with the text manifold, injecting a statistical linguistic bias that systematically overshadows fine-grained visual evidence. While prior work either aggressively closes this gap or suppresses hallucinations through expensive black-box decoding strategies, none addresses the underlying geometric cause. We provide the first quantitative characterization of this over-alignment, demonstrating that linguistic bias concentrates in the top principal components of a universal, dataset-agnostic text subspace. Building on this insight, we propose two complementary remedies: a training-free inference strategy and a bias-aware fine-tuning paradigm, both of which explicitly project out this subspace from visual representations. Our methods significantly reduce hallucinations across POPE, CHAIR, and AMBER benchmarks, and improve CLAIR scores on long-form captioning tasks, with the training-free variant adding no computational overhead over the base model.

16.
arXiv (quant-ph) 2026-06-16

A Gauge-Covariant Geometric Framework for Non-Hermitian Quantum Systems

arXiv:2606.15922v1 Announce Type: new Abstract: We develop a comprehensive, gauge-covariant geometric framework for non-Hermitian quantum systems in the quasi-Hermitian regime, that is, the region of parameter space where the non-Hermitian Hamiltonian admits a real spectrum and a positive-definite metric operator. We build this framework by elevating the Dyson map to a central geometric object. This map is the transformation that converts a non-Hermitian Hamiltonian into an equivalent Hermitian one. From it we construct the Dyson connection and decompose it into Hermitian and anti-Hermitian parts, identified respectively as {\it stretching } and {\it rotation } components. This decomposition cleanly separates the genuine physical metric deformations from the unitary gauge redundancies. Working with manifestly gauge-covariant states, we then derive the complex non-Hermitian Berry phase and the quantum geometric tensor (QGT), and show that the non-Hermitian geometric curvature originates from the non-commutativity of the stretching components at the operator level. We further analyse the geometric singularities near an exceptional point (EP) and uncover a distinct hierarchy of divergences. For a general two-level non-Hermitian model, the quantum metric tensor (QMT) exhibits a leading-order divergence $\sim |\epsilon_\mu|^{-2}$, while the Berry curvature shows a weaker, subleading divergence $\sim |\epsilon_\mu|^{-3/2}$, with $\epsilon_\mu$ denoting the parameter displacement from the EP along an individual parameter axis $\mu$. Finally, we examine physical realizations of this model, including the non-Hermitian Su–Schrieffer–Heeger (SSH) and Hatano–Nelson (HN) models, where exact analytical results confirm the predicted critical scaling laws and illustrate the metric-deformation-driven non-Hermitian geometries.

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

SPARX: Secure and Privacy-Aware Approximate CNN Acceleration with Edge RISC-V SoC

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computing improves hardware efficiency by exploiting the error resilience of neural network workloads; however, most approximate CNN accelerators do not jointly consider secure, privacy-aware edge deployment. This paper presents SPARX, a Secure and Privacy-Aware Approximate CNN Acceleration framework integrated within a heterogeneous RV32IMC RISC-V System-on-Chip (SoC). SPARX combines a custom RISC-V instruction extension, an approximate logarithmic CNN acceleration unit, a lightweight differential-noise-based privacy engine, and a challenge-response authentication mechanism. To guide arithmetic selection, an approximation-aware decision framework is introduced that uses the Approximation Severity Index (ASI), Approximation Efficiency (AE), Quality of Approximation (QoA), Approximation Figure-of-Merit (AFOM), and Hardware Acceleration Efficiency (HAE). Evaluation across 11 state-of-the-art approximate MAC architectures identifies the Iterative Logarithmic Multiplier (ILM) as the most suitable design, achieving 51.7% area reduction, 81.5% power reduction, and 2.13x throughput improvement compared with an accurate radix-4 Booth MAC, while only reducing ResNet-20/CIFAR-10 accuracy by 2.82 percentage points. FPGA implementation on a Xilinx VC707 platform achieves 58.4 GOPS/W energy efficiency at 250 MHz, while 28-nm CMOS physical implementation validates ASIC feasibility

18.
medRxiv (Medicine) 2026-06-10

"We don't complain; it's just part of being a woman": frequency, knowledge, and sociocultural beliefs about dysmenorrhoea in a South African university cohort

Introduction Dysmenorrhoea is highly prevalent globally and interferes with engagement in education, work, social participation, and quality of life. Although evidence suggests that sociocultural beliefs influence how menstrual pain is understood and managed, relatively little research has explored dysmenorrhoea-related knowledge and beliefs within South Africa. This study aimed to (1) determine the frequency of dysmenorrhoea, (2) assess dysmenorrhoea-related knowledge and compare knowledge between menstruating and non-menstruating individuals, and (3) explore commonly held generational, cultural, and religious beliefs related to dysmenorrhoea in a South African university cohort. Methods We analysed data collected as part of a cross-sectional survey conducted among staff and students at a South African university. Participants completed demographic questions, items assessing dysmenorrhoea-related knowledge, and an adapted Working Ability, Location, Intensity, Days of Pain, Dysmenorrhoea (WaLIDD) questionnaire. Participants were also invited to provide free-text responses describing generational, cultural, and religious beliefs about dysmenorrhoea. Quantitative data were analysed descriptively and compared between menstruating and non-menstruating participants. Free-text responses were analysed using reflexive thematic analysis. Results A total of 863 participants completed the survey, including 578 current or past menstruators. The frequency (95%CI) of dysmenorrhoea was 75.4% (71.7-78.9). Most participants were classified as having moderate (53%) or severe (31%) dysmenorrhoea on the WaLIDD scale. Awareness of dysmenorrhoea was higher among participants who had menstruated than among those who had never menstruated (80.4% vs 55.3%, p

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

Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytelling

arXiv:2602.04109v2 Announce Type: replace-cross Abstract: Conversational AI agents are increasingly explored as creative partners, yet how conversation design shapes child-AI dialogue in co-creative settings remains underexplored. We present Tinker Tales, a tangible dialogue system for child-AI collaborative storytelling, in which educational frameworks (narrative development and social-emotional learning) are instantiated as conversation design, shaping how the agent engages children across four narrative stages. The system combines a physical storytelling board, NFC-embedded toys, and a mobile app mediating multimodal interaction through tangible manipulation and voice-based dialogue. We conducted a home-based user study with 10 children (ages 6-8) across two conversation design conditions varying in how the agent structured elaboration, with and without educational scaffolding. Our findings show that prompt framing shapes the form and consistency of children's narrative contributions, structuring how they participate in co-creative dialogue with AI.

20.
arXiv (CS.AI) 2026-06-25

Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment

arXiv:2606.26071v1 Announce Type: cross Abstract: A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two steps, iterated as needed. First, we read the chain of thought (CoT) to generate hypotheses about what drives model behavior. Second, we make edits to the prompt or environment to test these hypotheses. While the CoT is not always faithful, it is a rich source of unsupervised insight that can guide the collection of more rigorous evidence. To evaluate our protocol, we create a suite of six agentic environments where models exhibit concerning behavior, and apply it to each. We establish that Kimi K2 Thinking takes shortcuts due to a genuine disposition towards low-effort actions, by showing this hypothesis successfully predicts its behavior. Through counterfactual experiments, we show DeepSeek R1 deceives out of a desire to be consistent with a previous instance of itself. Our methods nonetheless leave significant room for refinement. For example, when we test whether Kimi K2 Thinking believes it is violating user intent, we find no evidence of such a belief, but without positive controls we cannot confirm our tests would detect it. Overall, we find our simple protocol provides a strong baseline that we hope future work will improve upon. More broadly, our work is a concrete step in developing the growing field of model forensics.

21.
arXiv (CS.CL) 2026-06-17

Translating the Untranslatable: An Operationalizable Ontology for Untranslatability

Untranslatability, cases where meaning cannot be directly preserved across languages, is well-studied in linguistics but underexplored in NLP. As machine translation (MT) systems improve on standard benchmarks, their limitations increasingly concentrate in such cases, where translation cannot be reduced to one-to-one equivalence. We introduce a structured ontology of untranslatability along with a taxonomy of compensation strategies, which are specific techniques to convey meaning under these untranslatable circumstances. We operationalize this framework into a multilingual dataset of untranslatable sentences paired with strategy-based translations, enabling controlled analysis of translation behavior. Initial human preference studies suggest that translation quality depends on the strategy used, with consistent preferences for outputs that include explanatory context, known as the Annotation compensation strategy. Our framework and dataset provide a foundation for studying and modeling strategy-informed machine translation.

22.
medRxiv (Medicine) 2026-06-24

Breaking The Pain-Stiffness Cycle- Supraclavicular Catheter Facilitated Rehabilitation Of Post-Surgical Elbow stiffness- A Retrospective Observational Study

ABSTRACT Background: Post-traumatic elbow stiffness is a recognised complication following orthopaedic trauma surgery, occurring in 10-15% of trauma patients sustaining injuries. Pain remains the primary barrier to physiotherapy compliance, with surgical arthrolysis carrying recurrence rates of up to 34%. The supraclavicular brachial plexus block, referred to as the 'spinal of the arm', provides anaesthesia and analgesia to the entire upper limb below the shoulder. A structured non-surgical approach combining continuous catheter analgesia with timed rehabilitation was identified as an unmet need in this patient group. Methods: A single-centre retrospective observational study was conducted on data of patients treated for post-surgical upper limb stiffness between January 2022 and April 2026. Of 30 patients identified, 28 with elbow involvement formed the primary analysis group following exclusion of 2 patients with isolated wrist stiffness and complex regional pain syndrome. Ultrasound- guided supraclavicular brachial plexus catheters were inserted using the Contiplex system. Patients received 0.5% Bupivacaine (10-15ml) for initial blockade, followed by daily top-up doses of 0.2% Ropivacaine(20ml) given 30 minutes prior to structured physiotherapy and CPM sessions for up to 5 days. The primary outcome was change in arc of elbow motion in degrees, measured by the attending orthopaedic consultant using standard goniometry. Results: Complete pre- and post- intervention data were available for all 28 patients. Mean pre-intervention arc of elbow motion was 39.1{degrees}(SD+/-23.2{degrees}), improving to 104.2{degrees}(SD+/- 30.0{degrees}) post-intervention. Mean improvement was 65.1{degrees}(SD+/- 30.6{degrees} ); 95% CI 53.8{degrees} to 76.4{degrees} ; range 10{degrees}-140{degrees} ; paired t-test t=-11.27, p

23.
medRxiv (Medicine) 2026-06-10

A risk-of-contagion index using a Bayesian based model for the COVID-19 epidemic in Mexico

During the COVID-19 pandemic, limited testing capacity and reporting delays complicated epidemic surveillance and decision-making in Mexico. We calibrated textit{covidestim}, a Bayesian nowcasting model, to estimate the total SARS-CoV-2 infections from reported cases and deaths using Mexican surveillance data. Disease-progression distribution priors were calibrated using Mexico City records and validated through comparisons with national seroprevalence surveys, hospitalization data, and annual reported severe-case rates across all states. Using the reconstructed estimates of active infections, we implemented an event-based risk framework that quantifies the probability of encountering at least one infectious individual in gatherings of different sizes. This probability was subsequently translated into a four-level epidemiological traffic-light indicator and computed at both state and municipality levels. The resulting estimates revealed substantial spatial heterogeneity that is obscured by state-level aggregation, particularly in states with marked differences between urban and rural municipalities. To evaluate consistency with public-health indicators, we compared the proposed risk classification with the official Mexican epidemiological traffic-light system, considering interpretable gathering sizes relevant to public-health decision making. Weekly reports derived from this framework were delivered to policymakers in the State of Queretaro in Mexico, as an anticipation tool for school reopening and public-space management. This demonstrates that this Bayesian reconstruction of infections combined with event-based risk metrics can provide an interpretable and generalizable municipality-level complement to routine surveillance systems, particularly in regions with limited testing capacity and heterogeneous local transmission dynamics.

24.
arXiv (quant-ph) 2026-06-12

Diffusive Dynamics of Nonstabilizerness

arXiv:2606.13606v1 Announce Type: new Abstract: Symmetries shape the quantum-information dynamics of many-body systems, but their effect on nonstabilizerness, the resource complementary to entanglement, is less understood. We compute the stabilizer Rényi entropy, a measure of nonstabilizerness, in $\mathrm{U}(1)$-symmetric one-dimensional random circuits. The disorder-averaged dynamics is captured by a four-replica tensor network, which we evaluate by $S_4$-adapted infinite time-evolving block decimation (iTEBD) directly in the thermodynamic limit. Together with a hydrodynamic argument, our results identify a diffusive universality class for the late-time approach of nonstabilizerness to its random-state value, with the stabilizer Rényi entropy gap closing as $1/t$. The same scaling is verified in an energy-conserving nonintegrable Ising chain. More broadly, our framework provides a hydrodynamic perspective on nonstabilizerness generation and offers insight into the design of approximate Haar-random states in Hamiltonian dynamics.

25.
arXiv (CS.CL) 2026-06-16

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing speech language models rely on text supervision, hierarchical token streams, or complex hybrid architectures, departing from the single-stream generative pretraining paradigm that has proven effective in text. In this work, we introduce WavSLM, a speech language model trained by quantizing and distilling self-supervised WavLM representations into a single codebook and optimizing an autoregressive next-chunk prediction objective. WavSLM jointly models semantic and acoustic information within a single token stream without text supervision or text pretraining. Despite its simplicity, it achieves competitive performance on consistency benchmarks and speech generation while using fewer parameters, less training data, and supporting streaming inference.