{"total":15,"items":[{"citing_arxiv_id":"2606.26218","ref_index":234,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Dark Matter in Draco and Bo\\\"otes I: Hints of a Core in an Ultra-Faint Dwarf from Simulation-Based Inference","primary_cat":"astro-ph.GA","submitted_at":"2026-06-24T18:00:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GraphNPE recovers a significantly lower central density for Boötes I consistent with a core while Draco remains marginally cuspy, and demonstrates that higher-order velocity moments reduce bias in dynamical modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20906","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction","primary_cat":"cs.LG","submitted_at":"2026-06-18T20:03:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MMGNN decomposes molecular graphs into multi-color subgraphs by atom-type pairs and applies shared message-passing per subgraph, achieving top macro AUC-ROC of 0.838 on classification and best RMSE on ESOL and FreeSolv among tested models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07598","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embeddings on the n-Sphere","primary_cat":"cs.LG","submitted_at":"2026-05-29T07:21:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Trained MPNNs factor through bounded step-graphon-signals that embed via an explicit map into disjoint caps on the n-sphere, producing a topological fingerprint for model comparison and retrieval.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18188","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-18T10:28:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11610","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-12T06:42:00+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"generalization in atomistic models URLhttps://arxiv.org/abs/2601.08486 [42] Omee S S, Fu N, Dong R, Hu M and Hu J 2024 npj Computational Materials10 ISSN 2057-3960 URLhttp://dx.doi.org/10.1038/s41524-024-01316-4 [43] Liu Z, Wang Y, Vaidya S, Ruehle F, Halverson J, Soljaˇ ci' c M, Hou T Y and Tegmark M 2024 Kan: Kolmogorov-arnold networks URLhttps://arxiv.org/abs/2404. 19756 [44] Gilmer J, Schoenholz S S, Riley P F, Vinyals O and Dahl G E 2017 Neural message passing for quantum chemistry URLhttps://arxiv.org/abs/1704.01212 [45] Lim Y F, Ng C K, Vaitesswar U and Hippalgaonkar K 2021 Advanced Intelligent Systems3ISSN 2640-4567 URLhttp://dx.doi.org/10.1002/aisy.202100101 [46] Petersen M H, Zhu R, Dai H, Aggarwal S, Wei N, Chen A P, Bhowmik A, Lastra"},{"citing_arxiv_id":"2605.07812","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":1,"top_context_role":"background","top_context_polarity":"background","context_text":"across datasets. The unseen behavior can be interpreted as either an undocumented attack or a changed normal behavior. However, we consider these reports anomalous and analyze entries that clearly indicate unknown behavior separately. 7 Related work [12] builds on the insight that attacks can be reconstructed from only a few correctly identified nodes [39], [40], [41]. In the VELOXevaluation, a single node, regardless of type, is sufficient to mark an attack as detected. WithD(p)calculating the percentage of attacks detected with a precision ofp, defined by: D(p) = |{A i |A i ∩R(p)̸=∅ }| k whereA i is the node set of attackiamong the total ofk attacks, andR(p)are the reported nodes with precisionp."},{"citing_arxiv_id":"2605.03901","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Graph Neural Networks in the Wilson Loop Representation of Abelian Lattice Gauge Theories","primary_cat":"cond-mat.str-el","submitted_at":"2026-05-05T15:55:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A gauge-invariant GNN using Wilson loops as inputs accurately predicts observables and simulates dynamics in Z2 and U(1) lattice gauge models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20797","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gauge-Equivariant Graph Neural Networks for Lattice Gauge Theories","primary_cat":"cond-mat.str-el","submitted_at":"2026-04-22T17:21:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Gauge-equivariant graph neural networks embed non-Abelian local symmetries directly into message passing for lattice gauge theories, enabling learning of nonlocal observables from local operations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14685","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection","primary_cat":"cs.CR","submitted_at":"2026-04-16T06:40:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.05020","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-10-06T17:00:21+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.09323","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning-Optimized Qubit Mapping and Reuse to Minimize Inter-Core Communication in Modular Quantum Architectures","primary_cat":"quant-ph","submitted_at":"2025-06-11T01:52:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.15001","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening","primary_cat":"cs.LG","submitted_at":"2024-10-19T06:27:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FIT-GNN applies graph coarsening during inference to deliver orders-of-magnitude faster single-node inference and lower memory use on node and graph classification/regression tasks while keeping competitive accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2409.08036","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Heterogeneous Sheaf Neural Networks","primary_cat":"cs.LG","submitted_at":"2024-09-12T13:38:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2104.13478","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"structure that comes with differentiable manifolds, where such maps are calleddiffeomorphisms and denoted byDiff(Ω). Additional examples of struc- tures we will encounter includedistancesormetrics(maps preserving them are calledisometries) ororientation(to the best of our knowledge, orientation- preserving maps do not have a common Greek name). A metric or distance is a functiond : Ω× Ω→ [0,∞) satisfying for all u, v, w∈ Ω: Identity of indiscernibles:d(u, v) = 0 iff u = v. Symmetry: d(u, v) = d(v, u). Triangle inequality:d(u, v)≤ d(u, w) + d(w, v). A space equipped with a metric(Ω, d) is called ametric space. Therightlevelofstructuretoconsiderdependsontheproblem. Forexample, when segmenting histopathology slide images, we may wish to consider flipped versions of an image as equivalent (as the sample can be flipped when put under the microscope), but if we are trying to classify road signs, we would only want to consider orientation-preserving transformations as symmetries (since reflections could change the meaning of the sign). As we add levels of structure to be preserved, the symmetry group will get smaller. Indeed,addingstructureisequivalenttoselectinga subgroup,which is a subset of the larger group that satisfies the axioms of a group by itself: Let (G,◦) be a group andH⊆ G a subset.H is said to be asubgroupof G if (H,◦) constitutes a group with the same operation. For instance, the group of Euclidean isometriesE(2) is a subgroup of the groupofplanardiffeomorphisms Diff(2),andinturnthegroupoforientation- preserving isometriesSE(2) is a subgroup ofE(2). This hierarchy of struc- ture follows the Erlangen Programme philosophy outlined in the Preface: in Klein's construction, the Projective, Affine, and Euclidean geometries 3. GEOMETRIC PRIORS 19 have increasingly more invariants and correspond to progressively smaller groups. Isomorphisms and Automorphisms We have described symmetries as structure preserving and invertible mapsfrom an object to itself. Such maps are"},{"citing_arxiv_id":"1907.05315","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking","primary_cat":"cs.CV","submitted_at":"2019-07-11T15:43:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}