{"total":158,"items":[{"citing_arxiv_id":"2605.12326","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging","primary_cat":"cs.NE","submitted_at":"2026-05-12T16:08:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11854","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-12T09:39:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TABOM models inference unmasking preferences as a Boltzmann distribution over predictive entropies and derives a ranking loss to align DLM training with observed trajectories, yielding gains in new domains and reduced catastrophic forgetting versus standard SFT.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11829","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media","primary_cat":"physics.optics","submitted_at":"2026-05-12T09:17:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The BiLT autoencoder recovers absorption and scattering spectra from integrating sphere data with high accuracy while remaining robust to wavelength shifts up to 10 bands and generalizing to different instrument line shapes without retraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11479","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation","primary_cat":"cs.RO","submitted_at":"2026-05-12T03:54:30+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11274","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"End-to-End Population Inference from Gravitational-Wave Strain using Transformers","primary_cat":"gr-qc","submitted_at":"2026-05-11T21:54:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11111","ref_index":68,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ShardTensor: Domain Parallelism for Scientific Machine Learning","primary_cat":"cs.DC","submitted_at":"2026-05-11T18:20:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10772","ref_index":9,"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":"2605.10464","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Automated Detection of Abnormalities in Zebrafish Development","primary_cat":"cs.CV","submitted_at":"2026-05-11T12:33:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new annotated dataset of zebrafish embryo image sequences enables a spatiotemporal transformer to classify fertility at 98% accuracy and detect compound-induced malformations at 92% accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10123","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Complex-Valued Phase-Coherent Transformer","primary_cat":"cs.LG","submitted_at":"2026-05-11T07:38:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PCT replaces softmax token competition with a smooth phase-preserving gate on normalized complex similarities, yielding stronger generalization on long-range and phase-sensitive benchmarks than both real and complex Transformers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10023","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Search for invisible decays of light mesons via $J/\\psi \\to VP$ $(V=\\omega/\\phi,P=\\eta/\\eta')$ decays at STCF","primary_cat":"hep-ex","submitted_at":"2026-05-11T05:46:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Monte Carlo projections set 90% CL upper limits of 3.7e-7, 8.9e-7, 1.8e-7 and 4.1e-7 on invisible branching fractions of omega, phi, eta and eta' at STCF.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09949","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models","primary_cat":"cs.LG","submitted_at":"2026-05-11T03:53:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09881","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Dissecting Jet-Tagger Through Mechanistic Interpretability","primary_cat":"hep-ph","submitted_at":"2026-05-11T02:11:47+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11034","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining","primary_cat":"cs.CR","submitted_at":"2026-05-11T02:01:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A compact Mamba-2 model performs end-to-end byte-level network traffic classification without tokenization or pre-training and remains competitive with substantially larger pre-trained systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09842","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Yield Curve Forecasting using Machine Learning and Econometrics: A Comparative Analysis","primary_cat":"cs.AI","submitted_at":"2026-05-11T00:53:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"ARIMA and naive econometric models outperform machine learning and deep learning methods for US Treasury yield curve forecasting over 47 years, except in one time block, while TimeGPT, LGBM, and RNNs lead among ML approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09304","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Generating Complex Code Analyzers from Natural Language Questions","primary_cat":"cs.SE","submitted_at":"2026-05-10T04:02:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09226","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Quantum Injection Pathways for Implicit Graph Neural Networks","primary_cat":"quant-ph","submitted_at":"2026-05-09T23:51:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09150","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play","primary_cat":"cs.LG","submitted_at":"2026-05-09T20:26:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AlphaExploitem adds a hierarchical transformer encoder and a diverse pool of exploitable opponents to AlphaHoldem, enabling exploitation of suboptimal poker play while preserving performance against Nash-equilibrium opponents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09090","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations","primary_cat":"cs.CV","submitted_at":"2026-05-09T17:54:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Controlled counterfactual perturbations reveal no correlation between embedding cosine similarity and approximation behavior in two visual grounding models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08696","ref_index":51,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Structured Recurrent Mixers for Massively Parallelized Sequence Generation","primary_cat":"cs.CL","submitted_at":"2026-05-09T05:07:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07985","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation","primary_cat":"cs.DC","submitted_at":"2026-05-08T16:44:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dooly reduces LLM inference profiling costs by 56.4% via configuration-agnostic taint-based labeling and selective database reuse, delivering simulation accuracy within 5% MAPE for TTFT and 8% for TPOT across 12 models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08316","ref_index":153,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey","primary_cat":"cs.CR","submitted_at":"2026-05-08T14:58:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A literature survey synthesizes 119 studies on AI-driven alert screening into a four-stage taxonomy of filtering, triage, correlation, and generative augmentation while identifying gaps in deployment realism and robustness.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Representative Studies in Alert Correlation and Incident Reconstruction (continued) Study Year Method Dataset Key Metric Notable Finding / Limitation [161] Zeng et al. (SHADE- WATCHER) 2022 Graph recommendation + GNN for provenance- based detection DARPA TC DR 0.96; FPR 0.001 [T2] Recommendation framing enables scalable provenance GNN; full graph; high memory. [153] Wang et al. (threaTrace) 2022 Node-level provenance- graph learning for host- based threat detection DARPA TC; StreamSpot F1 0.978 node- level [T2] Fine-grained node classification; per-host, no cross-host correlation. [60] Hossain et al. (SLEUTH) 2017 Causal analysis: tag propagation + back- ward/forward tracing DARPA TC; syn- thetic APT Foundational"},{"citing_arxiv_id":"2605.07812","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification","primary_cat":"cs.CR","submitted_at":"2026-05-08T14:45:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07779","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Neural network quantum states in the grand canonical ensemble","primary_cat":"quant-ph","submitted_at":"2026-05-08T14:18:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new neural quantum state ansatz for bosons in the grand canonical ensemble achieves competitive variational energies in 1D and 2D systems and provides access to one-body reduced density matrices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07622","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Is She Even Relevant? When BERT Ignores Explicit Gender Cues","primary_cat":"cs.CL","submitted_at":"2026-05-08T11:48:22+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08300","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters","primary_cat":"cs.LG","submitted_at":"2026-05-08T11:37:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Manifold-constrained multi-stream mixing plus per-stream adapters improves SSM language model validation loss from 6.3507 to 6.1353 and perplexity from 572.91 to 461.88 on WikiText-2.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07193","ref_index":14,"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":"2605.07127","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Position Curse: LLMs Struggle to Locate the Last Few Items in a List","primary_cat":"cs.LG","submitted_at":"2026-05-08T02:04:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06591","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation","primary_cat":"cs.LG","submitted_at":"2026-05-07T17:19:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06578","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach","primary_cat":"eess.SP","submitted_at":"2026-05-07T17:07:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A gated-fusion CSI predictor using GRU, attention, and DSLH reaches -13.84 dB NMSE with 26% fewer parameters and 2.3x higher throughput than a LinFormer baseline on 3GPP channels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06394","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Lecture Notes on Statistical Physics and Neural Networks","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-05-07T15:08:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Lecture notes that treat statistical physics as probability theory and connect Ising models, spin glasses, and renormalization group ideas to Hopfield networks, restricted Boltzmann machines, and large language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06374","ref_index":45,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ResiHP: Taming LLM Training Failures with Dynamic Hybrid Parallelism","primary_cat":"cs.DC","submitted_at":"2026-05-07T14:52:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"ResiHP introduces a workload-aware failure detector and dynamic scheduler for hybrid-parallel LLM training that achieves 1.04-4.39x higher throughput than prior resilient systems under failures on a 256-GPU cluster.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06270","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-05-07T13:45:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Asymmetric token reduction, with distinct merging for queries and pruning for key-values plus layer-wise adaptation, delivers up to 28x speedup on 1000-frame 3D reconstruction inputs while preserving competitive quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06206","ref_index":25,"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":"2605.06040","ref_index":21,"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":"2605.06033","ref_index":33,"ref_count":3,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge","primary_cat":"cs.DL","submitted_at":"2026-05-07T11:23:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AI use in science has grown exponentially since 2015 but stays confined to computer science and statistics topics, shows higher retraction rates and citations, and follows distinct global adoption patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05907","ref_index":56,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience","primary_cat":"q-bio.NC","submitted_at":"2026-05-07T09:17:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Decoding alignment metrics can remain high and unchanged even when encoding manifold topology is causally altered, so they do not imply similar function or computation across neural populations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05049","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Piper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism","primary_cat":"cs.DC","submitted_at":"2026-05-06T15:47:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Piper introduces resource modeling and pipelined hybrid parallelism for MoE training, delivering 2-3.5X higher MFU than prior frameworks and 1.2-9X better all-to-all bandwidth.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05267","ref_index":122,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","primary_cat":"cs.SE","submitted_at":"2026-05-06T09:38:31+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Copilot Evaluation[88], HallTrigger[103], GitHub Copilot, Amazon CodeWhisperer, ChatGPT[142], Codequal Analyzer[105], Unveiling Inefficiencies in LLM-Generated Code[1], Python Tests Quality[5], CoQuIR[30], REAL[141], Infinite-Instruct[137], Quality In, Quality Out[45], Security and Quality in LLM-Generated Code[54], ROSE[91], Refining ChatGPT-Generated Code[76], Seed-Coder[110], CodeSmellEval[122], Beyond Correctness[152], Path Planning Evaluation[15], CODEJUDGE[119], Code Generation Survey[51], DataRecipe[55], MultiCodeIF[25], Beyond Functional Correctness[127] Understandability Unveiling Inefficiencies in LLM-Generated Code[1], CIDRe[26], Security and Quality in LLM-Generated Code[54], Seed-Coder[110], CRPE[35], CodeSmellEval[122], Beyond"},{"citing_arxiv_id":"2605.04587","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Mitigating stellar radial velocity jitter using orthogonal activity indices and a time-aware neural network","primary_cat":"astro-ph.EP","submitted_at":"2026-05-06T07:36:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A convolutional attention network trained on StarSim synthetic data reduces radial velocity RMS from stellar activity to 52.5% and 62.4% of original levels in two real stars and yields tighter orbital parameters for TZ Arietis b than Gaussian process regression.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04434","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"A CNN--Transformer Denoiser for low-$S/N$ Galaxy Spectra: Stellar Population Recovery in Synthetic Tests","primary_cat":"astro-ph.GA","submitted_at":"2026-05-06T02:54:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A hybrid CNN-Transformer denoiser trained on synthetic spectra substantially reduces noise and improves stellar population recovery for low-S/N galaxy observations in controlled tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04355","ref_index":57,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making","primary_cat":"cs.CV","submitted_at":"2026-05-05T23:24:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Integrating DVS event data into InterFuser through token fusion yields a driving score of 77.2 and 100% route completion on CARLA benchmarks, indicating improved robustness in dynamic conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04107","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments","primary_cat":"cs.SE","submitted_at":"2026-05-04T15:35:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02604","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model","primary_cat":"cs.CV","submitted_at":"2026-05-04T13:51:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02337","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training","primary_cat":"cs.DC","submitted_at":"2026-05-04T08:41:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedPLT assigns client-specific model layers for training and matches or beats full-model federated learning accuracy with 71-82 percent fewer trainable parameters per client.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01484","ref_index":105,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","primary_cat":"cs.LG","submitted_at":"2026-05-02T15:11:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"due to the context length of LLMs. Instead, depend- ing on the task, we can summarize the statistics of the walks that can easily scale with the graph size. 4 Estimation of Graph Properties 4.1 Estimation of Number of Nodes and Edges Estimating the size of a graph and other proper- ties has been extensively studied in the graph lit- Graph description: [(149, 32), (145, 220), (126, 222), (15, 77), (190, 191), (223, 224), (18, 232), (137, 174), (18, 19), (247, 52), (157, 178), (11, 162), (160, 2), (174, 246), (114, 37), (120, 213), (132, 133), (5, 11), (3, 4), (142, 53), (24, 29), (105, 101), (5, 13), (112, 56), (31, 34), (165, 106), (32, 236), (220, 203), (230, 231), (143, 145), (17, 20), (35, 36), (158, 30), (14, 66), (89, 91), (156, 157), (95, 61), (135, 172), (112, 138), (161, 56), (123, 106), (147, 150), (145, 136), (198, 90), (18, 20), (202, 13), (33, 114), (39, 40), (143, 144), (82, 84), (5, 14), (169, 168), (119, 213), (240, 171), (121, 192), (239, 95), (126, 218), (44, 87), (197, 198), (240, 167), (43, 169), (18, 53), (89, 90), (0, 2), (98, 95), (207, 168), (5, 15), (114, 68), (47, 48), (92, 96), (74, 32), (216, 240), (67, 70), (46, 167), (156, 158), (132, 136), (55, 245), (155, 168), (133, 2), (32, 227) …+Task description Random Walks RW-1 description …RW-2 description …RW-3 description …RW-4 description …Task description+ [ ] [ ] Running out of context length LLM full graph description Graph description within context length Figure 2: Figure illustrates the issue of exceeding context length as the graph size increases. Random walks on graphs provide efficient way of extracting and encoding graph-related information. erature especially for social networks like Face- book or Twitter."},{"citing_arxiv_id":"2605.01072","ref_index":17,"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":"2605.00412","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling","primary_cat":"cs.AI","submitted_at":"2026-05-01T05:09:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hamiltonian World Models structure latent dynamics around energy-conserving Hamiltonian evolution to produce physically grounded, action-controllable predictions for embodied decision making.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00373","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Language-free Experience at Expo 2025 Osaka","primary_cat":"cs.CL","submitted_at":"2026-05-01T03:28:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"The paper reports the development and real-world deployment of simultaneous interpretation technologies using chunk-based segmentation, context-aware translation, and multi-engine MT at Expo 2025 Osaka.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00206","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:30:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SST V2 introduces parallel-trainable nonlinear recurrence in latent space to let transformers reason continuously across positions, delivering +15 points on GPQA-Diamond and halving remaining GSM8K errors over matched baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00195","ref_index":50,"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}],"limit":50,"offset":0}