{"total":15,"items":[{"citing_arxiv_id":"2606.31832","ref_index":37,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Navigating committor landscape of biomolecules with a general pairwise interaction model","primary_cat":"physics.comp-ph","submitted_at":"2026-06-30T15:37:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A novel neural architecture based on Pairformer is introduced for learning committor functions to better capture dynamical features in biomolecular rare events without specialized priors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28458","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"mCGCNN: A Dual-Stream Crystal Graph Convolutional Neural Network for the Efficient Prediction of Magnetic Properties of Crystalline Materials","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-26T12:17:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"mCGCNN augments crystal graph networks with a magnetic stream and GKA-inspired descriptors to lower MAE for total magnetic moment from 2.54 to 2.02 μB and raise R² from 0.644 to 0.776 on Materials Project DFT data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09520","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration","primary_cat":"physics.chem-ph","submitted_at":"2026-06-08T14:09:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLM molecular design framework uses self-reflection on full physicochemical data from first-principles calculations to achieve low deviation on HOMO-LUMO gaps and generalize to other properties.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09480","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction","primary_cat":"cs.LG","submitted_at":"2026-06-08T13:39:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Loss-guided adaptive scale refinement on NaCl aqueous system reduces overall force MAE from 399.65 to 381.23 by discovering intermediate scales from initial anchors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07567","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SurfDesign: Effective Protein Design on Molecular Surfaces","primary_cat":"q-bio.BM","submitted_at":"2026-05-25T19:53:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23708","ref_index":215,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Dynamic Stability Landscapes in Synchronization Networks","primary_cat":"cs.LG","submitted_at":"2026-05-22T14:55:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18404","ref_index":38,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials","primary_cat":"cs.DC","submitted_at":"2026-05-18T13:45:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"JanusPipe introduces SymFold and WaveK to enable efficient 3D-parallel training for conservative MLIPs, reporting 1.51x and 1.45x average throughput gains over 1F1B and Hanayo baselines on 32 GPUs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13262","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10458","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space","primary_cat":"cs.LG","submitted_at":"2026-05-11T12:29:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"QT-Net predicts atomic electron populations and multipoles via a new SOAP-cluster held-out test, improving molecular property prediction and recovering QM9 dipole moments from per-atom outputs.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"In all models, node features are initialized with a message passing layer as follows: h(0) i = LayerNorm  X j MLP (EMBED(Zi),EMBED(Z j))⊙Γ ( ˆrij,RBF(r ij))   ,(1) 5 where Zi, Zj, are the atomic species. Γ is a geometric gate with tanh activation output that takes as input the components of the inter-atom displacement vector, concatenated to a projection onto radial basis functions (RBFs) as implemented in DimeNet [12]: RBFn(r) = r 2 c sin(nπr/c) r 1 + cos(πr/c) 2 . Edge features are initialized from these node features as follows h(0) ij = LayerNorm  MLP  LayerNorm   X k∈{i,j} MLP \u0010 h(0) k \u0011     ⊙Γ \u0010 ˆGij,RBF(r ij) \u0011   , (2) where ˆGij ∝ ˆrij ⊗ ˆrT ij is the edge's normalized gyration tensor expressed in the traceless symmetric representation. See Section A."},{"citing_arxiv_id":"2605.02267","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Composition-Weighted Symbolic Regression for General-Purpose Property Prediction","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-04T06:20:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A composition-weighted symbolic regression framework learns analytical expressions and elemental weightings from composition to predict materials properties with accuracy competitive to black-box models while producing explicit, constraint-enforcing formulas.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06336","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning","primary_cat":"cs.LG","submitted_at":"2026-04-07T18:16:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BiScale-GTR achieves claimed state-of-the-art results on MoleculeNet, PharmaBench and LRGB by combining improved fragment tokenization with a parallel GNN-Transformer architecture that operates at both atom and fragment scales.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.10315","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Infusing Experimental Reality into Complex Many-Body Hamiltonians: The Observable-Constrained Variational Framework (OCVF)","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-12-11T06:07:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"OCVF adds a learned neural-network correction to a skeleton Hamiltonian so that the model matches experimental PDF constraints, yielding up to 95.8% better accuracy on BaTiO3 phase-transition temperatures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.03046","ref_index":59,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","primary_cat":"cs.LG","submitted_at":"2025-10-03T14:28:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.14665","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Accurate and scalable exchange-correlation with deep learning","primary_cat":"physics.chem-ph","submitted_at":"2025-06-17T15:56:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Skala is a neural XC functional trained on wavefunction data that beats state-of-the-art hybrids on main-group chemistry benchmarks at semi-local computational cost.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"org/10.1080/00268970802708959. [61] J. Řezáč. Non-Covalent Interactions Atlas Benchmark Data Sets 2: Hydrogen Bonding in an Extended Chemical Space. Journal of Chemical Theory and Computation, 16(10):6305-6316, Oct. 2020. ISSN 1549- 9618. doi: 10.1021/acs.jctc.0c00715. URL https://doi.org/10.1021/acs.jctc.0c00715. Publisher: American Chemical Society. [62] J. Řezáč. Non-Covalent Interactions Atlas Benchmark Data Sets: Hydrogen Bonding.Journal of Chemical Theory and Computation, 16(4):2355-2368, Apr. 2020. ISSN 1549-9618. doi: 10.1021/acs.jctc.9b01265. URL https://doi.org/10.1021/acs.jctc.9b01265. Publisher: American Chemical Society. [63] K. Kříž, M. Nováček, and J. Řezáč. Non-Covalent Interactions Atlas Benchmark Data Sets 3: Repulsive"},{"citing_arxiv_id":"2104.13478","ref_index":48,"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"}],"limit":50,"offset":0}