{"total":148,"items":[{"citing_arxiv_id":"2605.13634","ref_index":40,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Europe and the Geopolitics of AGI: The Need for a Preparedness Plan","primary_cat":"cs.CY","submitted_at":"2026-05-13T15:00:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"AGI may arrive by 2030-2040 and reshape global power balances, requiring Europe to close gaps in compute, talent retention, industrial adoption, and unified policy responses through a coordinated preparedness agenda.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12809","ref_index":241,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:01:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12763","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"State-Space NTK Collapse Near Bifurcations","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12671","ref_index":114,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","primary_cat":"cs.CL","submitted_at":"2026-05-12T19:21:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLM tasks are supported by multiple distinct circuits rather than unique mechanisms, demonstrated via Overlap-Aware Sheaf Repulsion and the Distributive Dense Circuit Hypothesis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12484","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:58:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Fast-Slow Training combines slow parameter updates with fast context optimization to achieve up to 3x better sample efficiency, higher performance, less forgetting, and preserved plasticity in continual LLM learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11333","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces","primary_cat":"cs.DC","submitted_at":"2026-05-11T23:38:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Chakra introduces a portable, interoperable graph-based execution trace format for distributed ML workloads along with supporting tools to standardize performance benchmarking and software-hardware co-design.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10772","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:05:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A fine-tuned large language-vision model achieves 98% accuracy on visual question answering for military vehicle identification in SAR imagery from an extended MSTAR benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10286","ref_index":83,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","primary_cat":"cs.AI","submitted_at":"2026-05-11T09:46:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09498","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Spectral Transformer Neural Processes","primary_cat":"cs.LG","submitted_at":"2026-05-10T12:17:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"STNPs extend TNPs with a spectral aggregator that estimates context spectra, forms spectral mixtures, and injects task-adaptive frequency features to better handle periodicity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08898","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"LLM-Agnostic Semantic Representation Attack","primary_cat":"cs.CL","submitted_at":"2026-05-09T11:43:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08871","ref_index":135,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","primary_cat":"math.OC","submitted_at":"2026-05-09T10:46:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08842","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"XPERT: Expert Knowledge Transfer for Effective Training of Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-09T09:53:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"XPERT extracts and reuses cross-domain expert knowledge from pre-trained MoE LLMs via inference analysis and tensor decomposition to improve performance and convergence in downstream language model training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08746","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Global Empirical NTK: Self-Referential Bias and Dimensionality of Gradient Descent Learning","primary_cat":"cs.LG","submitted_at":"2026-05-09T07:22:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The global empirical NTK for finite-width networks has a universal Kronecker-core form that makes it structurally low-rank and biases gradient descent toward dominant modes of joint input-hidden activity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08416","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Alignment as Jurisprudence","primary_cat":"cs.AI","submitted_at":"2026-05-08T19:22:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Jurisprudence and AI alignment share core structures in predicting and shaping decisions by powerful actors through language specification and interpretation, enabling mutual insights.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07795","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","primary_cat":"math.OC","submitted_at":"2026-05-08T14:32:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07565","ref_index":95,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Ensemble Distributionally Robust Bayesian Optimisation","primary_cat":"cs.LG","submitted_at":"2026-05-08T10:37:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07358","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:10:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07193","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Coupling Models for One-Step Discrete Generation","primary_cat":"cs.LG","submitted_at":"2026-05-08T03:40:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07172","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization","primary_cat":"cs.CL","submitted_at":"2026-05-08T03:07:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Topology-enhanced alignment via persistent homology on trajectories outperforms standard SFT and DPO baselines on preference metrics for LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07096","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Query-efficient model evaluation using cached responses","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:24:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DKPS-based methods leverage cached model responses to achieve equivalent benchmark prediction accuracy with substantially fewer queries than standard evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06206","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Federation of Experts: Communication Efficient Distributed Inference for Large Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-07T13:12:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FoE restructures MoE blocks into per-KV-head clusters with sum-based synchronization, removing all-to-all communication in single-node settings and limiting it to intra-node in multi-node settings for up to 5.2x faster inference with comparable quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06098","ref_index":41,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Exploring the Effectiveness of Abstract Syntax Tree Patterns for Algorithm Recognition","primary_cat":"cs.SE","submitted_at":"2026-05-07T12:16:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An AST pattern-matching prototype with a custom DSL achieves 0.74 average F1-score on a BigCloneEval subset, outperforming CodeLlama (0.35) and code clone detectors (best recall 0.20).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06040","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning","primary_cat":"cs.AI","submitted_at":"2026-05-07T11:28:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Novelty estimation via LLM prompts enables pruning in Tree-of-Thought search, reducing overall token usage on language planning benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05365","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ZAYA1-8B Technical Report","primary_cat":"cs.AI","submitted_at":"2026-05-06T18:44:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04449","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","primary_cat":"cs.CL","submitted_at":"2026-05-06T03:25:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04208","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages","primary_cat":"cs.CL","submitted_at":"2026-05-05T18:47:46+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Nsanku benchmark shows current LLMs achieve only modest zero-shot translation scores on 43 Ghanaian languages, with no model reaching both high average performance and high cross-language consistency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03799","ref_index":26,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF","primary_cat":"cs.CL","submitted_at":"2026-05-05T14:25:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"The work provides a reproducible, session-based guide to the NLP pipeline with original adaptations and resources for morphologically rich low-resource languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03515","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-05T08:52:14+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05244","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","primary_cat":"cs.IR","submitted_at":"2026-05-04T11:28:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02300","ref_index":246,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"A Meta Reinforcement Learning Approach to Goals-Based Wealth Management","primary_cat":"cs.LG","submitted_at":"2026-05-04T07:48:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01441","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Artificial intelligence language technologies in multilingual healthcare: Grand challenges ahead","primary_cat":"cs.CL","submitted_at":"2026-05-02T13:39:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A narrative review of AI language technologies in multilingual healthcare identifies performance gaps in safety and equity and proposes seven grand challenges centered on reliability, human oversight, and cross-disciplinary collaboration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01072","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reconstructing conformal field theoretical compositions with Transformers","primary_cat":"hep-th","submitted_at":"2026-05-01T20:09:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Transformers reconstruct the constituent RCFTs in tensor-product theories from low-energy spectra, reaching 98% accuracy on WZW models and generalizing to larger central charges with few out-of-domain examples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00955","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems","primary_cat":"cs.CR","submitted_at":"2026-05-01T12:30:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"E-MIA converts document details into four types of exam questions and aggregates the RAG's answers into a membership score that separates member and non-member documents better than prior similarity-based or probe-based attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02939","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework","primary_cat":"cs.LG","submitted_at":"2026-05-01T07:57:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AuDisAgent reformulates multimodal controversy detection as a dynamic audience dissemination process using screening, panel discussion, and arbitration agents, plus comment bootstrapping, and reports outperforming prior static methods on a public dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00195","ref_index":49,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Diversity in Large Language Models under Supervised Fine-Tuning","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:20:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27384","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RCW-CIM: A Digital CIM-based LLM Accelerator with Read-Compute/Write","primary_cat":"cs.AR","submitted_at":"2026-04-30T03:52:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RCW-CIM reduces Llama2-7B decoding latency by 21.59% and prefill latency by 49.76% via minimized weight updates and DRAM accesses, delivering 3.28 TOPS and 42.3 TOPS/W on a fabricated 22 nm chip.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27311","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Pragmos: A Process Agentic Modeling System","primary_cat":"cs.SE","submitted_at":"2026-04-30T01:49:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Pragmos is a hybrid interactive system that decomposes process modeling into explainable steps using LLMs augmented by behavioral-relation tools to produce sound and comprehensible models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27124","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-04-29T19:23:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Sigmoid attention replaces softmax in single-cell foundation models to deliver better representations, faster training, and stability, backed by bounded derivatives, diagonal Jacobian, and a new efficient GPU kernel.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.26587","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Sparse-on-Dense: Area and Energy-Efficient Computing of Sparse Neural Networks on Dense Matrix Multiplication Accelerators","primary_cat":"cs.AR","submitted_at":"2026-04-29T12:10:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Sparse neural networks achieve better area and energy efficiency when executed on dense matrix multiplication accelerators using a Sparse-on-Dense approach than on dedicated sparse accelerators.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27006","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Accuracy: LLM Variability in Evidence Screening for Software Engineering SLRs","primary_cat":"cs.SE","submitted_at":"2026-04-29T08:55:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLMs exhibit substantial heterogeneity and non-determinism in SLR evidence screening, abstracts are decisive for performance, and they show no reliable superiority over classical classifiers on two real SLRs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24662","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","primary_cat":"physics.data-an","submitted_at":"2026-04-27T16:24:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24203","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing","primary_cat":"cs.CR","submitted_at":"2026-04-27T09:07:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Agentic Witnessing enables privacy-preserving auditing of semantic properties in private data by running an LLM auditor in a TEE that answers binary queries and produces cryptographic transcripts of its reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23471","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Can Humans Detect AI? Mining Textual Signals of AI-Assisted Writing Under Varying Scrutiny Conditions","primary_cat":"cs.HC","submitted_at":"2026-04-25T23:34:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Warned AI-assisted writers had their documents selected as human 54.13% of the time by judges versus 45.87% for unwarned writers, despite no measurable differences in text features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23371","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When Context Sticks: Studying Interference in In-Context Learning","primary_cat":"cs.LG","submitted_at":"2026-04-25T16:35:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"In-context learning shows persistent interference from prior examples, with more misleading linear examples degrading quadratic predictions and training curricula modulating recovery speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23347","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Evaluating Large Language Models on Computer Science University Exams in Data Structures","primary_cat":"cs.CL","submitted_at":"2026-04-25T15:08:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A new benchmark of Tel Aviv University data structures exams is used to evaluate GPT-4o, Claude 3.5, Mathstral 7B, and LLaMA 3 8B on closed and multiple-choice questions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23338","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","primary_cat":"cs.CR","submitted_at":"2026-04-25T14:57:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23051","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Evaluating Temporal Consistency in Multi-Turn Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-24T22:44:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Language models frequently violate temporal scope stability in multi-turn dialogues by drifting toward present-day assumptions even when they possess the correct facts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22925","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Come Together: Analyzing Popular Songs Through Statistical Embeddings","primary_cat":"stat.AP","submitted_at":"2026-04-24T18:00:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Logistic PCA embeddings of musical features enable statistical analysis of clustering by album and stylistic changes in Beatles songs by Lennon and McCartney.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21431","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"JAX-BEM: Gradient-Based Acoustic Shape Optimisation via a Differentiable Boundary Element Method","primary_cat":"cs.CE","submitted_at":"2026-04-23T08:48:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A JAX-based differentiable BEM solver matches traditional BEM accuracy on benchmarks and supports gradient-driven acoustic geometry optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21223","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model","primary_cat":"cs.CL","submitted_at":"2026-04-23T02:37:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"IRM derives implicit reward signals from off-the-shelf LLMs to detect generated text zero-shot and reports better results than prior zero-shot and supervised detectors on the DetectRL benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}